Category

Voice & audio

Agents that listen and speak: real-time voice assistants and phone agents, speech-to-text and transcription tools built on models such as Whisper, text-to-speech and voice cloning, and music and sound generation.

1,779 agents · 4 subcategories · mostly Python, Typescript, Javascript

Voice & audio by type

  • pipecat · Open Source framework for voice agents, multimodal apps, and realtime AI. Mainta
  • agents · A framework for building realtime voice AI agents 🤖🎙️📹
  • speech-to-speech · Build voice agents with open-source models
See all 995 →
  • whisper · Robust Speech Recognition via Large-Scale Weak Supervision
  • whisper.cpp · Port of OpenAI's Whisper model in C/C++
  • faster-whisper · Faster Whisper transcription with CTranslate2
See all 381 →
  • bark · 🔊 Text-Prompted Generative Audio Model
  • YuE · YuE2: frontier music generation with symbolic planning, zero-shot covers, and ag
  • podcastfy · An Open Source Python alternative to NotebookLM's podcast feature: Transforming
See all 208 →
  • ChatTTS · A generative speech model for daily dialogue.
  • CosyVoice · Multi-lingual large voice generation model, providing inference, training and de
  • CosyVoice · Multi-lingual large voice generation model, providing inference, training and de
See all 194 →

Every agent in Voice & audio, most starred first

whisper★ 113,157

Robust Speech Recognition via Large-Scale Weak Supervision

whisper.cpp★ 55,362

Port of OpenAI's Whisper model in C/C++

ChatTTS★ 40,028

A generative speech model for daily dialogue.

bark★ 39,379

🔊 Text-Prompted Generative Audio Model

faster-whisper★ 26,889

Faster Whisper transcription with CTranslate2

CosyVoice★ 24,461

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

CosyVoice★ 22,022

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Speech★ 18,770

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

pipecat★ 17,359

Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.

agents★ 15,285

A framework for building realtime voice AI agents 🤖🎙️📹

tortoise-tts★ 14,895

A multi-voice TTS system trained with an emphasis on quality

speech-to-speech★ 13,757

Build voice agents with open-source models

YuE★ 13,624

YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.

openwhispr★ 11,911

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

moonshine★ 11,570

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

ten-framework★ 11,241

Open-source framework for conversational voice AI agents

AudioGPT★ 10,173

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Vision-Agents★ 8,216

Quickly build text, voice and video agents. Fast, Go based Agent backend with SDKs for every language. Sensible defaults for search, knowledge, skills, telephony, sandboxes, memory and persistence. Sovereign AI. Take control of your AI.

vibe★ 8,176

Transcribe on your own!

wukong-robot★ 7,132

🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目,支持ChatGPT多轮对话能力,还可能是首个支持脑机交互的开源智能音箱项目。

openai-realtime-agents★ 7,018

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

podcastfy★ 6,830

An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI

call-center-ai★ 6,704

Send a phone call from AI agent, in an API call. Or, directly call the bot from the configured phone number!

SmartSub★ 6,115

视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字,批量处理 + 全平台 GPU 加速,跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitles — local Whisper speech-to-text, AI dubbing & voice cloning, offline, GPU-accelerated.

earshot★ 5,286

Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.

01★ 5,154

The #1 open-source voice interface for desktop, mobile, and ESP32 chips.

WhisperLive★ 4,361

A nearly-live implementation of OpenAI's Whisper.

vocode-core★ 3,807

🤖 Build voice-based LLM agents. Modular + open source.

openai-realtime-console★ 3,617

React app for inspecting, building and debugging with the Realtime API

auto-subs★ 3,450

Instantly generate AI-powered subtitles on your device. Works standalone or connects to DaVinci Resolve.

suno-api★ 3,319

Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.

TTS-WebUI★ 3,315

A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!

qwen-audio-agent★ 3,259

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

whisper-standalone-win★ 3,245

Whisper & Faster-Whisper standalone executables for those who don't want to bother with Python.

faster-whisper-GUI★ 2,999

faster_whisper GUI with PySide6

vexa★ 2,999

Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

VoiceMem★ 2,904

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

speechgpt★ 2,740

💬 SpeechGPT is a web application that enables you to converse with ChatGPT.

Android-MVVM-Architecture-Android-Voice-AI-SDK★ 2,580

Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin

Agnentic-Voice-AI-SDK★ 2,579

Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin

awesome-whisper★ 2,435

🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

openai-edge-tts★ 2,172

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

baresip★ 2,150

Baresip is a modular SIP User-Agent with audio and video support

openvidu★ 2,147

OpenVidu Platform: self-hosted real-time video and audio for your apps, built on LiveKit and mediasoup

ElatoAI★ 2,123

Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets & Edge Functions for AI Toys, Desk Companions and Devices

epub_to_audiobook★ 2,083

EPUB to audiobook converter, optimized for Audiobookshelf, WebUI included

CyberVerse★ 2,026

Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

alan-sdk-ios★ 1,874

The Self-Coding System for Your App — Alan AI SDK for iOS

bailing★ 1,794

百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断

xiaozhi-android-client★ 1,676

一个基于小智、xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本,打通IOS、Android端。请同志们动动小手,点点小星星,予以鼓励。

subwave★ 1,672

Personal internet radio: Agentic AI DJ

sokuji★ 1,505

Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app.

voicemode★ 1,473

Natural voice conversations with Claude Code

yt-whisper★ 1,442

Using OpenAI's Whisper to automatically generate YouTube subtitles

handcrafted-persona-engine★ 1,402

An AI-powered interactive avatar engine using Live2D, LLM, ASR, TTS, and RVC. Ideal for VTubing, streaming, and virtual assistant applications.

whisper-ctranslate2★ 1,374

Whisper command line client compatible with original OpenAI client based on CTranslate2.

ChatdollKit★ 1,287

ChatdollKit enables you to make your 3D model into a chatbot

AVA-AI-Voice-Agent-for-Asterisk★ 1,227

An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP/Websocket technology https://demo.agent6789.com

stenoai★ 1,136

Steno is the AI notepad for all your confidential conversations. On Windows & MacOS. Perfect for government, defence, legal and CXOs.

alan-sdk-cordova★ 1,129

The Self-Coding System for Your App — Alan AI SDK for Cordova

AI-Waifu-Vtuber★ 1,124

AI Vtuber for Streaming on Youtube/Twitch

Whisperboard★ 1,112

The open-source iOS app that's making quality voice transcription more accessible on mobile devices.

whisper-writer★ 1,108

💬📝 A small dictation app using OpenAI's Whisper speech recognition model.

realtime-phone-agents-course★ 1,090

Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.

Patter★ 1,086

Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines — Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo.

Tel-Agent★ 1,086

AI phone assistant | open-source

voquill★ 1,031

Open source voice dictation technology

openai-realtime-api-beta★ 1,023

Node.js + JavaScript reference client for the Realtime API (beta)

jarvis★ 1,014

JARVIS — a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.

agent-starter-react★ 968

A complete voice AI frontend app for LiveKit Agents with Next.js

local-talking-llm★ 896

A talking LLM that runs on your own computer without needing the internet.

heard★ 884

Open-source (Apache 2.0) voice tool for Claude Code and Codex on macOS that reads your coding agent's progress aloud. The voice runs locally with Kokoro, no account needed, or bring your own ElevenLabs or Speechify key. Hear a short spoken summary when your agent finishes, fails or needs approval.

agents-js★ 876

Build realtime multimodal AI agents with Node.js

CyberVerse★ 857

Open-source real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

whisper-playground★ 836

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

bolna★ 831

Conversational voice AI agents

Linguflex★ 812

Command Your World with Voice

whisper.rn★ 809

React Native binding of whisper.cpp.

june★ 787

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

use-whisper★ 785

React hook for OpenAI Whisper with speech recorder, real-time transcription, and silence removal built-in

SwiftWhisper★ 785

🎤 The easiest way to transcribe audio in Swift

whisper.unity★ 761

Running speech to text model (whisper.cpp) in Unity3d on your local machine.

voice-ai★ 760

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

LocalAIVoiceChat★ 741

Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.

ttsfm★ 738

TTSFM mirrors OpenAI's TTS service, providing a compatible interface for text-to-speech conversion with multiple voice options for free.

ai-native-callcenter★ 700

Self-hosted API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. Runs on FreeSWITCH with your SIP trunk and realtime model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).

chatterbox-tts-api★ 699

Local, OpenAI-compatible text-to-speech (TTS) API using Chatterbox, enabling users to generate voice cloned speech anywhere the OpenAI API is used (e.g. Open WebUI, AnythingLLM, etc.)

whisper_android★ 693

Offline Speech Recognition with OpenAI Whisper and TensorFlow Lite for Android

voice-assistant-scripts★ 681

Example scripts for AI agents created with the Alan AI Platform.

tapq★ 648

Multi-modal voice agent for your AI agents. Talk with Claude Code, Codex, and others by voice: answer their prompts, give instructions, ask what they did. Or just nod.

speech-to-text★ 613

Real-time transcription using faster-whisper

echokit_server★ 591

Open Source Voice Agent Platform

Starmoon★ 546

A conversational, AI device + software framework for companionship, entertainment, education, healthcare, IoT applications, and DIY robotics. Built with Python, NextJS, Arduino, ESP32, LLMs (GPT-4o), Deepgram STT and Azure TTS 🤖

decipher★ 544

Effortlessly add AI-generated transcription subtitles to your videos

whisplay-ai-chatbot★ 544

Pocket-sized AI chatbot built using a RPI Zero 2w / 5

JARVIS★ 528

Your own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interface

ollama-voice-mac★ 518

Mac compatible Ollama Voice

QuickVoice★ 496

Open-source, self-hostable platform for building and operating AI phone agents.

Lampline★ 495

Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.

gemini-live-api-examples★ 488

Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.

Questions

What makes a voice agent feel real-time?

Low latency at every hop: streaming speech recognition, a model that starts answering before the user finishes, and streaming speech synthesis. Most voice agent frameworks are built around that pipeline.

Is voice cloning allowed?

Laws differ by country and use. Only clone voices you have permission to use; several projects here ship consent checks or watermarking.

Frameworks used in Voice & audio

Other categories