cai/ref/voice/input/index.html

3365 lines
76 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="icon" href="../../../assets/imago.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.11">
<title>Input - CAI</title>
<link rel="stylesheet" href="../../../assets/stylesheets/main.4af4bdda.min.css">
<link rel="stylesheet" href="../../../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../../../stylesheets/extra.css">
<script>__md_scope=new URL("../../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="custom" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#input" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../../.." title="CAI" class="md-header__button md-logo" aria-label="CAI" data-md-component="logo">
<img src="../../../assets/imago.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
CAI
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Input
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/aliasrobotics/cai" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8M97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
aliasrobotics/cai
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../../.." title="CAI" class="md-nav__button md-logo" aria-label="CAI" data-md-component="logo">
<img src="../../../assets/imago.png" alt="logo">
</a>
CAI
</label>
<div class="md-nav__source">
<a href="https://github.com/aliasrobotics/cai" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8M97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
aliasrobotics/cai
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_1" >
<label class="md-nav__link" for="__nav_1" id="__nav_1_label" tabindex="">
<span class="md-ellipsis">
Getting Started
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1">
<span class="md-nav__icon md-icon"></span>
Getting Started
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../.." class="md-nav__link">
<span class="md-ellipsis">
Welcome
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai_installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai_quickstart/" class="md-nav__link">
<span class="md-ellipsis">
Quickstart
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai_list_of_models/" class="md-nav__link">
<span class="md-ellipsis">
Available Models
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_1_5" >
<label class="md-nav__link" for="__nav_1_5" id="__nav_1_5_label" tabindex="0">
<span class="md-ellipsis">
Model Providers
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_1_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1_5">
<span class="md-nav__icon md-icon"></span>
Model Providers
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../providers/openrouter.md" class="md-nav__link">
<span class="md-ellipsis">
OpenRouter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../providers/ollama/" class="md-nav__link">
<span class="md-ellipsis">
Ollama
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../providers/azure.md" class="md-nav__link">
<span class="md-ellipsis">
Azure OpenAI
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../../cai_pro/" class="md-nav__link">
<span class="md-ellipsis">
🚀 CAI PRO
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-ellipsis">
Core Concepts
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Core Concepts
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../cai_architecture/" class="md-nav__link">
<span class="md-ellipsis">
Architecture
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../agents/" class="md-nav__link">
<span class="md-ellipsis">
Agents
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tools/" class="md-nav__link">
<span class="md-ellipsis">
Tools
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../handoffs/" class="md-nav__link">
<span class="md-ellipsis">
Handoffs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../multi_agent/" class="md-nav__link">
<span class="md-ellipsis">
Multi-Agent Systems
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-ellipsis">
Benchmarking
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Benchmarking
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../benchmarking/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../benchmarking/running_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Running Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../benchmarking/attack_defense/" class="md-nav__link">
<span class="md-ellipsis">
Attack & Defense CTFs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../benchmarking/jeopardy_ctfs/" class="md-nav__link">
<span class="md-ellipsis">
Jeopardy CTFs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../benchmarking/cyber_ranges/" class="md-nav__link">
<span class="md-ellipsis">
Cyber Ranges
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../benchmarking/knowledge_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Knowledge Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../benchmarking/privacy_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Privacy Benchmarks
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="">
<span class="md-ellipsis">
Guides
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Guides
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../running_agents/" class="md-nav__link">
<span class="md-ellipsis">
Running Agents
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../continue_mode/" class="md-nav__link">
<span class="md-ellipsis">
Continue Mode
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../results/" class="md-nav__link">
<span class="md-ellipsis">
Working with Results
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../streaming/" class="md-nav__link">
<span class="md-ellipsis">
Streaming
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tracing/" class="md-nav__link">
<span class="md-ellipsis">
Tracing & Debugging
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../context/" class="md-nav__link">
<span class="md-ellipsis">
Context Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../guardrails/" class="md-nav__link">
<span class="md-ellipsis">
Guardrails & Security
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../environment_variables/" class="md-nav__link">
<span class="md-ellipsis">
Environment Variables
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai/getting-started/packet_capture_wsl/" class="md-nav__link">
<span class="md-ellipsis">
Packet Capture on WSL2
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="">
<span class="md-ellipsis">
Troubleshooting
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Troubleshooting
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../cai/troubleshooting/operator_feedback_reproduction/" class="md-nav__link">
<span class="md-ellipsis">
Operator Feedback Reproduction
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai/troubleshooting/platform_limitations/" class="md-nav__link">
<span class="md-ellipsis">
Platform Limitations
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="">
<span class="md-ellipsis">
Case Studies
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Case Studies
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../cai/case-studies/operator-artifact-evidence/" class="md-nav__link">
<span class="md-ellipsis">
Operator Artifact Evidence
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_8" >
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="">
<span class="md-ellipsis">
Mobile UI (iOS)
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_8">
<span class="md-nav__icon md-icon"></span>
Mobile UI (iOS)
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../mui/mui_index/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../mui/getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../mui/user_interface/" class="md-nav__link">
<span class="md-ellipsis">
User Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../mui/gestures_shortcuts/" class="md-nav__link">
<span class="md-ellipsis">
Gestures & Shortcuts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../mui/chat_features/" class="md-nav__link">
<span class="md-ellipsis">
Chat Features
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_9" >
<label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="">
<span class="md-ellipsis">
Terminal UI (TUI) - Deprecated
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_9">
<span class="md-nav__icon md-icon"></span>
Terminal UI (TUI) - Deprecated
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../tui/tui_index/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/user_interface/" class="md-nav__link">
<span class="md-ellipsis">
User Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/terminals_management/" class="md-nav__link">
<span class="md-ellipsis">
Terminals Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/teams_and_parallel_execution/" class="md-nav__link">
<span class="md-ellipsis">
Teams & Parallel Execution
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/sidebar_features/" class="md-nav__link">
<span class="md-ellipsis">
Sidebar Features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/keyboard_shortcuts/" class="md-nav__link">
<span class="md-ellipsis">
Keyboard Shortcuts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/commands_reference/" class="md-nav__link">
<span class="md-ellipsis">
Commands Reference
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/advanced_features/" class="md-nav__link">
<span class="md-ellipsis">
Advanced Features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../tui/troubleshooting/" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10" >
<label class="md-nav__link" for="__nav_10" id="__nav_10_label" tabindex="">
<span class="md-ellipsis">
API Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_10_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10">
<span class="md-nav__icon md-icon"></span>
API Reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_1" >
<label class="md-nav__link" for="__nav_10_1" id="__nav_10_1_label" tabindex="0">
<span class="md-ellipsis">
Agents
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_1">
<span class="md-nav__icon md-icon"></span>
Agents
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../agent/" class="md-nav__link">
<span class="md-ellipsis">
Agent
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../run/" class="md-nav__link">
<span class="md-ellipsis">
Runner
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tool/" class="md-nav__link">
<span class="md-ellipsis">
Tool
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../result/" class="md-nav__link">
<span class="md-ellipsis">
Result
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../stream_events/" class="md-nav__link">
<span class="md-ellipsis">
Stream Events
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../handoffs/" class="md-nav__link">
<span class="md-ellipsis">
Handoffs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../lifecycle/" class="md-nav__link">
<span class="md-ellipsis">
Lifecycle
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../items/" class="md-nav__link">
<span class="md-ellipsis">
Items
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../run_context/" class="md-nav__link">
<span class="md-ellipsis">
Run Context
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../usage/" class="md-nav__link">
<span class="md-ellipsis">
Usage
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../exceptions/" class="md-nav__link">
<span class="md-ellipsis">
Exceptions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../guardrail/" class="md-nav__link">
<span class="md-ellipsis">
Guardrail
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../model_settings/" class="md-nav__link">
<span class="md-ellipsis">
Model Settings
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../agent_output/" class="md-nav__link">
<span class="md-ellipsis">
Agent Output
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../function_schema/" class="md-nav__link">
<span class="md-ellipsis">
Function Schema
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_2" >
<label class="md-nav__link" for="__nav_10_2" id="__nav_10_2_label" tabindex="0">
<span class="md-ellipsis">
Models
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_2">
<span class="md-nav__icon md-icon"></span>
Models
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../models/interface/" class="md-nav__link">
<span class="md-ellipsis">
Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../models/openai_chatcompletions/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Chat Completions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../models/openai_responses/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Responses
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_3" >
<label class="md-nav__link" for="__nav_10_3" id="__nav_10_3_label" tabindex="0">
<span class="md-ellipsis">
Extensions
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_3">
<span class="md-nav__icon md-icon"></span>
Extensions
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../extensions/handoff_filters/" class="md-nav__link">
<span class="md-ellipsis">
Handoff Filters
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../extensions/handoff_prompt/" class="md-nav__link">
<span class="md-ellipsis">
Handoff Prompt
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_11" >
<label class="md-nav__link" for="__nav_11" id="__nav_11_label" tabindex="">
<span class="md-ellipsis">
Advanced
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_11_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_11">
<span class="md-nav__icon md-icon"></span>
Advanced
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../cai_development/" class="md-nav__link">
<span class="md-ellipsis">
Development
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_12" >
<label class="md-nav__link" for="__nav_12" id="__nav_12_label" tabindex="">
<span class="md-ellipsis">
Research
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_12_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_12">
<span class="md-nav__icon md-icon"></span>
Research
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../research/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_13" >
<label class="md-nav__link" for="__nav_13" id="__nav_13_label" tabindex="">
<span class="md-ellipsis">
Resources
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_13_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_13">
<span class="md-nav__icon md-icon"></span>
Resources
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../../cai_faq/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai_find_us/" class="md-nav__link">
<span class="md-ellipsis">
Find Us
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../../cai_citation_and_acknowledgments/" class="md-nav__link">
<span class="md-ellipsis">
Citation & Acknowledgments
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input" class="md-nav__link">
<span class="md-ellipsis">
input
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput" class="md-nav__link">
<span class="md-ellipsis">
AudioInput
</span>
</a>
<nav class="md-nav" aria-label="AudioInput">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput.buffer" class="md-nav__link">
<span class="md-ellipsis">
buffer
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput.frame_rate" class="md-nav__link">
<span class="md-ellipsis">
frame_rate
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput.sample_width" class="md-nav__link">
<span class="md-ellipsis">
sample_width
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput.channels" class="md-nav__link">
<span class="md-ellipsis">
channels
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput.to_audio_file" class="md-nav__link">
<span class="md-ellipsis">
to_audio_file
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.AudioInput.to_base64" class="md-nav__link">
<span class="md-ellipsis">
to_base64
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.StreamedAudioInput" class="md-nav__link">
<span class="md-ellipsis">
StreamedAudioInput
</span>
</a>
<nav class="md-nav" aria-label="StreamedAudioInput">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#cai.sdk.agents.voice.input.StreamedAudioInput.add_audio" class="md-nav__link">
<span class="md-ellipsis">
add_audio
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="input"><code>Input</code></h1>
<div class="doc doc-object doc-module">
<a id="cai.sdk.agents.voice.input"></a>
<div class="doc doc-contents first">
<div class="doc doc-children">
<div class="doc doc-object doc-class">
<h3 id="cai.sdk.agents.voice.input.AudioInput" class="doc doc-heading">
<span class="doc doc-object-name doc-class-name">AudioInput</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-dataclass"><code>dataclass</code></small>
</span>
</h3>
<div class="doc doc-contents ">
<p>Static audio to be used as input for the VoicePipeline.</p>
<details class="quote">
<summary>Source code in <code>src/cai/sdk/agents/voice/input.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">40</span>
<span class="normal">41</span>
<span class="normal">42</span>
<span class="normal">43</span>
<span class="normal">44</span>
<span class="normal">45</span>
<span class="normal">46</span>
<span class="normal">47</span>
<span class="normal">48</span>
<span class="normal">49</span>
<span class="normal">50</span>
<span class="normal">51</span>
<span class="normal">52</span>
<span class="normal">53</span>
<span class="normal">54</span>
<span class="normal">55</span>
<span class="normal">56</span>
<span class="normal">57</span>
<span class="normal">58</span>
<span class="normal">59</span>
<span class="normal">60</span>
<span class="normal">61</span>
<span class="normal">62</span>
<span class="normal">63</span>
<span class="normal">64</span>
<span class="normal">65</span>
<span class="normal">66</span>
<span class="normal">67</span>
<span class="normal">68</span>
<span class="normal">69</span>
<span class="normal">70</span>
<span class="normal">71</span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-40"><span class="nd">@dataclass</span>
</span><span id="__span-0-41"><span class="k">class</span><span class="w"> </span><span class="nc">AudioInput</span><span class="p">:</span>
</span><span id="__span-0-42"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Static audio to be used as input for the VoicePipeline.&quot;&quot;&quot;</span>
</span><span id="__span-0-43">
</span><span id="__span-0-44"> <span class="n">buffer</span><span class="p">:</span> <span class="n">npt</span><span class="o">.</span><span class="n">NDArray</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span> <span class="o">|</span> <span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">]</span>
</span><span id="__span-0-45"><span class="w"> </span><span class="sd">&quot;&quot;&quot;</span>
</span><span id="__span-0-46"><span class="sd"> A buffer containing the audio data for the agent. Must be a numpy array of int16 or float32.</span>
</span><span id="__span-0-47"><span class="sd"> &quot;&quot;&quot;</span>
</span><span id="__span-0-48">
</span><span id="__span-0-49"> <span class="n">frame_rate</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="n">DEFAULT_SAMPLE_RATE</span>
</span><span id="__span-0-50"><span class="w"> </span><span class="sd">&quot;&quot;&quot;The sample rate of the audio data. Defaults to 24000.&quot;&quot;&quot;</span>
</span><span id="__span-0-51">
</span><span id="__span-0-52"> <span class="n">sample_width</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">2</span>
</span><span id="__span-0-53"><span class="w"> </span><span class="sd">&quot;&quot;&quot;The sample width of the audio data. Defaults to 2.&quot;&quot;&quot;</span>
</span><span id="__span-0-54">
</span><span id="__span-0-55"> <span class="n">channels</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span>
</span><span id="__span-0-56"><span class="w"> </span><span class="sd">&quot;&quot;&quot;The number of channels in the audio data. Defaults to 1.&quot;&quot;&quot;</span>
</span><span id="__span-0-57">
</span><span id="__span-0-58"> <span class="k">def</span><span class="w"> </span><span class="nf">to_audio_file</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">,</span> <span class="nb">str</span><span class="p">]:</span>
</span><span id="__span-0-59"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a tuple of (filename, bytes, content_type)&quot;&quot;&quot;</span>
</span><span id="__span-0-60"> <span class="k">return</span> <span class="n">_buffer_to_audio_file</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_rate</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sample_width</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">channels</span><span class="p">)</span>
</span><span id="__span-0-61">
</span><span id="__span-0-62"> <span class="k">def</span><span class="w"> </span><span class="nf">to_base64</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
</span><span id="__span-0-63"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the audio data as a base64 encoded string.&quot;&quot;&quot;</span>
</span><span id="__span-0-64"> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="o">.</span><span class="n">dtype</span> <span class="o">==</span> <span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">:</span>
</span><span id="__span-0-65"> <span class="c1"># convert to int16</span>
</span><span id="__span-0-66"> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">,</span> <span class="o">-</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>
</span><span id="__span-0-67"> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">*</span> <span class="mi">32767</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span><span class="p">)</span>
</span><span id="__span-0-68"> <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="o">.</span><span class="n">dtype</span> <span class="o">!=</span> <span class="n">np</span><span class="o">.</span><span class="n">int16</span><span class="p">:</span>
</span><span id="__span-0-69"> <span class="k">raise</span> <span class="n">UserError</span><span class="p">(</span><span class="s2">&quot;Buffer must be a numpy array of int16 or float32&quot;</span><span class="p">)</span>
</span><span id="__span-0-70">
</span><span id="__span-0-71"> <span class="k">return</span> <span class="n">base64</span><span class="o">.</span><span class="n">b64encode</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="o">.</span><span class="n">tobytes</span><span class="p">())</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">&quot;utf-8&quot;</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<div class="doc doc-object doc-attribute">
<h4 id="cai.sdk.agents.voice.input.AudioInput.buffer" class="doc doc-heading">
<span class="doc doc-object-name doc-attribute-name">buffer</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="n">buffer</span><span class="p">:</span> <span class="n"><span title="cai.sdk.agents.voice.imports.npt.NDArray">NDArray</span></span><span class="p">[</span><span class="n"><span title="cai.sdk.agents.voice.imports.np.int16">int16</span></span> <span class="o">|</span> <span class="n"><span title="cai.sdk.agents.voice.imports.np.float32">float32</span></span><span class="p">]</span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>A buffer containing the audio data for the agent. Must be a numpy array of int16 or float32.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h4 id="cai.sdk.agents.voice.input.AudioInput.frame_rate" class="doc doc-heading">
<span class="doc doc-object-name doc-attribute-name">frame_rate</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="n">frame_rate</span><span class="p">:</span> <span class="n"><span title="int">int</span></span> <span class="o">=</span> <span class="n"><span title="cai.sdk.agents.voice.input.DEFAULT_SAMPLE_RATE">DEFAULT_SAMPLE_RATE</span></span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>The sample rate of the audio data. Defaults to 24000.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h4 id="cai.sdk.agents.voice.input.AudioInput.sample_width" class="doc doc-heading">
<span class="doc doc-object-name doc-attribute-name">sample_width</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="n">sample_width</span><span class="p">:</span> <span class="n"><span title="int">int</span></span> <span class="o">=</span> <span class="mi">2</span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>The sample width of the audio data. Defaults to 2.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h4 id="cai.sdk.agents.voice.input.AudioInput.channels" class="doc doc-heading">
<span class="doc doc-object-name doc-attribute-name">channels</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="n">channels</span><span class="p">:</span> <span class="n"><span title="int">int</span></span> <span class="o">=</span> <span class="mi">1</span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>The number of channels in the audio data. Defaults to 1.</p>
</div>
</div>
<div class="doc doc-object doc-function">
<h4 id="cai.sdk.agents.voice.input.AudioInput.to_audio_file" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">to_audio_file</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="nf">to_audio_file</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="n"><span title="tuple">tuple</span></span><span class="p">[</span><span class="n"><span title="str">str</span></span><span class="p">,</span> <span class="n"><span title="io.BytesIO">BytesIO</span></span><span class="p">,</span> <span class="n"><span title="str">str</span></span><span class="p">]</span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>Returns a tuple of (filename, bytes, content_type)</p>
<details class="quote">
<summary>Source code in <code>src/cai/sdk/agents/voice/input.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">58</span>
<span class="normal">59</span>
<span class="normal">60</span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-58"><span class="k">def</span><span class="w"> </span><span class="nf">to_audio_file</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">io</span><span class="o">.</span><span class="n">BytesIO</span><span class="p">,</span> <span class="nb">str</span><span class="p">]:</span>
</span><span id="__span-0-59"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns a tuple of (filename, bytes, content_type)&quot;&quot;&quot;</span>
</span><span id="__span-0-60"> <span class="k">return</span> <span class="n">_buffer_to_audio_file</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">frame_rate</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">sample_width</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">channels</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
</details>
</div>
</div>
<div class="doc doc-object doc-function">
<h4 id="cai.sdk.agents.voice.input.AudioInput.to_base64" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">to_base64</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="nf">to_base64</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="n"><span title="str">str</span></span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>Returns the audio data as a base64 encoded string.</p>
<details class="quote">
<summary>Source code in <code>src/cai/sdk/agents/voice/input.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">62</span>
<span class="normal">63</span>
<span class="normal">64</span>
<span class="normal">65</span>
<span class="normal">66</span>
<span class="normal">67</span>
<span class="normal">68</span>
<span class="normal">69</span>
<span class="normal">70</span>
<span class="normal">71</span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-62"><span class="k">def</span><span class="w"> </span><span class="nf">to_base64</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
</span><span id="__span-0-63"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the audio data as a base64 encoded string.&quot;&quot;&quot;</span>
</span><span id="__span-0-64"> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="o">.</span><span class="n">dtype</span> <span class="o">==</span> <span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">:</span>
</span><span id="__span-0-65"> <span class="c1"># convert to int16</span>
</span><span id="__span-0-66"> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">clip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="p">,</span> <span class="o">-</span><span class="mf">1.0</span><span class="p">,</span> <span class="mf">1.0</span><span class="p">)</span>
</span><span id="__span-0-67"> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">=</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span> <span class="o">*</span> <span class="mi">32767</span><span class="p">)</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span><span class="p">)</span>
</span><span id="__span-0-68"> <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="o">.</span><span class="n">dtype</span> <span class="o">!=</span> <span class="n">np</span><span class="o">.</span><span class="n">int16</span><span class="p">:</span>
</span><span id="__span-0-69"> <span class="k">raise</span> <span class="n">UserError</span><span class="p">(</span><span class="s2">&quot;Buffer must be a numpy array of int16 or float32&quot;</span><span class="p">)</span>
</span><span id="__span-0-70">
</span><span id="__span-0-71"> <span class="k">return</span> <span class="n">base64</span><span class="o">.</span><span class="n">b64encode</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">buffer</span><span class="o">.</span><span class="n">tobytes</span><span class="p">())</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s2">&quot;utf-8&quot;</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
</details>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h3 id="cai.sdk.agents.voice.input.StreamedAudioInput" class="doc doc-heading">
<span class="doc doc-object-name doc-class-name">StreamedAudioInput</span>
</h3>
<div class="doc doc-contents ">
<p>Audio input represented as a stream of audio data. You can pass this to the <code>VoicePipeline</code>
and then push audio data into the queue using the <code>add_audio</code> method.</p>
<details class="quote">
<summary>Source code in <code>src/cai/sdk/agents/voice/input.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">74</span>
<span class="normal">75</span>
<span class="normal">76</span>
<span class="normal">77</span>
<span class="normal">78</span>
<span class="normal">79</span>
<span class="normal">80</span>
<span class="normal">81</span>
<span class="normal">82</span>
<span class="normal">83</span>
<span class="normal">84</span>
<span class="normal">85</span>
<span class="normal">86</span>
<span class="normal">87</span>
<span class="normal">88</span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-74"><span class="k">class</span><span class="w"> </span><span class="nc">StreamedAudioInput</span><span class="p">:</span>
</span><span id="__span-0-75"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Audio input represented as a stream of audio data. You can pass this to the `VoicePipeline`</span>
</span><span id="__span-0-76"><span class="sd"> and then push audio data into the queue using the `add_audio` method.</span>
</span><span id="__span-0-77"><span class="sd"> &quot;&quot;&quot;</span>
</span><span id="__span-0-78">
</span><span id="__span-0-79"> <span class="k">def</span><span class="w"> </span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
</span><span id="__span-0-80"> <span class="bp">self</span><span class="o">.</span><span class="n">queue</span><span class="p">:</span> <span class="n">asyncio</span><span class="o">.</span><span class="n">Queue</span><span class="p">[</span><span class="n">npt</span><span class="o">.</span><span class="n">NDArray</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span> <span class="o">|</span> <span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">]]</span> <span class="o">=</span> <span class="n">asyncio</span><span class="o">.</span><span class="n">Queue</span><span class="p">()</span>
</span><span id="__span-0-81">
</span><span id="__span-0-82"> <span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">add_audio</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">audio</span><span class="p">:</span> <span class="n">npt</span><span class="o">.</span><span class="n">NDArray</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span> <span class="o">|</span> <span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">]):</span>
</span><span id="__span-0-83"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Adds more audio data to the stream.</span>
</span><span id="__span-0-84">
</span><span id="__span-0-85"><span class="sd"> Args:</span>
</span><span id="__span-0-86"><span class="sd"> audio: The audio data to add. Must be a numpy array of int16 or float32.</span>
</span><span id="__span-0-87"><span class="sd"> &quot;&quot;&quot;</span>
</span><span id="__span-0-88"> <span class="k">await</span> <span class="bp">self</span><span class="o">.</span><span class="n">queue</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">audio</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<div class="doc doc-object doc-function">
<h4 id="cai.sdk.agents.voice.input.StreamedAudioInput.add_audio" class="doc doc-heading">
<span class="doc doc-object-name doc-function-name">add_audio</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-async"><code>async</code></small>
</span>
</h4>
<div class="language-python doc-signature highlight"><pre><span></span><code><span id="__span-0-1"><span class="nf">add_audio</span><span class="p">(</span><span class="n">audio</span><span class="p">:</span> <span class="n"><span title="cai.sdk.agents.voice.imports.npt.NDArray">NDArray</span></span><span class="p">[</span><span class="n"><span title="cai.sdk.agents.voice.imports.np.int16">int16</span></span> <span class="o">|</span> <span class="n"><span title="cai.sdk.agents.voice.imports.np.float32">float32</span></span><span class="p">])</span>
</span></code></pre></div>
<div class="doc doc-contents ">
<p>Adds more audio data to the stream.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>audio</code>
</td>
<td>
<code><span title="cai.sdk.agents.voice.imports.npt.NDArray">NDArray</span>[<span title="cai.sdk.agents.voice.imports.np.int16">int16</span> | <span title="cai.sdk.agents.voice.imports.np.float32">float32</span>]</code>
</td>
<td>
<div class="doc-md-description">
<p>The audio data to add. Must be a numpy array of int16 or float32.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<details class="quote">
<summary>Source code in <code>src/cai/sdk/agents/voice/input.py</code></summary>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">82</span>
<span class="normal">83</span>
<span class="normal">84</span>
<span class="normal">85</span>
<span class="normal">86</span>
<span class="normal">87</span>
<span class="normal">88</span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-82"><span class="k">async</span> <span class="k">def</span><span class="w"> </span><span class="nf">add_audio</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">audio</span><span class="p">:</span> <span class="n">npt</span><span class="o">.</span><span class="n">NDArray</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">int16</span> <span class="o">|</span> <span class="n">np</span><span class="o">.</span><span class="n">float32</span><span class="p">]):</span>
</span><span id="__span-0-83"><span class="w"> </span><span class="sd">&quot;&quot;&quot;Adds more audio data to the stream.</span>
</span><span id="__span-0-84">
</span><span id="__span-0-85"><span class="sd"> Args:</span>
</span><span id="__span-0-86"><span class="sd"> audio: The audio data to add. Must be a numpy array of int16 or float32.</span>
</span><span id="__span-0-87"><span class="sd"> &quot;&quot;&quot;</span>
</span><span id="__span-0-88"> <span class="k">await</span> <span class="bp">self</span><span class="o">.</span><span class="n">queue</span><span class="o">.</span><span class="n">put</span><span class="p">(</span><span class="n">audio</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
</details>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "../../..", "features": ["content.code.copy", "content.code.select", "navigation.path", "navigation.sections", "navigation.expand", "content.code.annotate"], "search": "../../../assets/javascripts/workers/search.f8cc74c7.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../../assets/javascripts/bundle.c8b220af.min.js"></script>
</body>
</html>