Voice & Speech AI Repositories

whisper

by openai

Total Stargazers:108940

Total Subscribers:782

Robust Speech Recognition via Large-Scale Weak Supervision

GPT-SoVITS

by RVC-Boss

Total Stargazers:61729

Total Subscribers:286

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Real-Time-Voice-Cloning

by CorentinJ

Total Stargazers:60128

Total Subscribers:937

Clone a voice in 5 seconds to generate arbitrary speech in real-time

whisper.cpp

by ggml-org

Total Stargazers:53623

Total Subscribers:408

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

voicebox

by jamiepine

Total Stargazers:53041

Total Subscribers:245

The open-source AI voice studio. Clone, dictate, create.

airi

by moeru-ai

Total Stargazers:49074

Total Subscribers:193

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.

TTS

by coqui-ai

Total Stargazers:46001

Total Subscribers:343

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

ChatTTS

by 2noise

Total Stargazers:39828

Total Subscribers:209

A generative speech model for daily dialogue.

Retrieval-based-Voice-Conversion-WebUI

by RVC-Project

Total Stargazers:38207

Total Subscribers:235

Easily train a good VC model with voice data <= 10 mins!

VoxCPM

by OpenBMB

Total Stargazers:36972

Total Subscribers:162

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

MockingBird

by babysor

Total Stargazers:36909

Total Subscribers:304

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

fish-speech

by fishaudio

Total Stargazers:32662

Total Subscribers:167

SOTA Open Source TTS

Handy

by cjpais

Total Stargazers:31434

Total Subscribers:97

A free, open source, and extensible speech-to-text application that works completely offline.

meetily

by Zackriya-Solutions

Total Stargazers:30672

Total Subscribers:146

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows. Understand How to write meeting minutes

openai-agents-python

by openai

Total Stargazers:29384

Total Subscribers:233

A lightweight, powerful framework for multi-agent workflows

chatterbox

by resemble-ai

Total Stargazers:26373

Total Subscribers:155

SoTA open-source TTS

llamafile

by mozilla-ai

Total Stargazers:25955

Total Subscribers:229

Distribute and run LLMs with a single file.

faster-whisper

by SYSTRAN

Total Stargazers:25358

Total Subscribers:172

Faster Whisper transcription with CTranslate2

whisperX

by m-bain

Total Stargazers:24000

Total Subscribers:161

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

index-tts

by index-tts

Total Stargazers:23912

Total Subscribers:134

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

CosyVoice

by QwenAudio

Total Stargazers:23585

Total Subscribers:136

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

VoiceStudio

by debpalash

Total Stargazers:23344

Total Subscribers:93

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

buzz

by chidiwilliams

Total Stargazers:21450

Total Subscribers:111

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

voice-changer

by w-okada

Total Stargazers:20967

Total Subscribers:184

リアルタイムボイスチェンジャー Realtime Voice Changer

FunASR

by modelscope

Total Stargazers:20285

Total Subscribers:118

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

ebook2audiobook

by DrewThomasson

Total Stargazers:20158

Total Subscribers:89

Generate audiobooks from e-books, voice cloning & 1158+ languages!

pydantic-ai

by pydantic

Total Stargazers:19877

Total Subscribers:124

How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

dia

by nari-labs

Total Stargazers:19399

Total Subscribers:167

A TTS model capable of generating ultra-realistic dialogue in one pass.

pyvideotrans

by jianchang512

Total Stargazers:18977

Total Subscribers:111

Translate the video from one language to another and embed dubbing & subtitles.

Speech

by NVIDIA-NeMo

Total Stargazers:18433

Total Subscribers:235

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)

VideoLingo

by Huanshere

Total Stargazers:18426

Total Subscribers:107

Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | Netflix级字幕切割、翻译、对齐、甚至加上配音，一键全自动视频搬运AI字幕组

kaldi

by kaldi-asr

Total Stargazers:15481

Total Subscribers:681

kaldi-asr/kaldi is the official location of the Kaldi project.

pipecat

by pipecat-ai

Total Stargazers:15461

Total Subscribers:84

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

KittenTTS

by KittenML

Total Stargazers:15446

Total Subscribers:132

State-of-the-art TTS model under 25MB 😻

F5-TTS

by SWivid

Total Stargazers:15223

Total Subscribers:133

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Duix-Avatar

by duixcom

Total Stargazers:15202

Total Subscribers:234

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

vosk-api

by alphacep

Total Stargazers:15126

Total Subscribers:142

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

sherpa-onnx

by k2-fsa

Total Stargazers:14735

Total Subscribers:121

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

agents

by livekit

Total Stargazers:14152

Total Subscribers:107

A framework for building realtime voice AI agents 🤖🎙️📹

supertonic

by supertone-oss-archive

Total Stargazers:13776

Total Subscribers:97

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Open-LLM-VTuber

by Open-LLM-VTuber

Total Stargazers:13711

Total Subscribers:103

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms

omi

by BasedHardware

Total Stargazers:13461

Total Subscribers:91

AI that sees your screen, listens to your conversations and tells you what to do

Qwen3-TTS

by QwenLM

Total Stargazers:13361

Total Subscribers:73

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

speech-to-speech

by huggingface

Total Stargazers:13171

Total Subscribers:105

Build voice agents with open-source models

insanely-fast-whisper

by Vaibhavs10

Total Stargazers:13059

Total Subscribers:87

______________

voice-pro

by abus-aikorea

Total Stargazers:12794

Total Subscribers:80

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

PaddleSpeech

by PaddlePaddle

Total Stargazers:12682

Total Subscribers:187

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

OmniVoice

by k2-fsa

Total Stargazers:12660

Total Subscribers:66

High-Quality Voice Cloning TTS for 600+ Languages

edge-tts

by rany2

Total Stargazers:11922

Total Subscribers:81

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

seamless_communication

by facebookresearch

Total Stargazers:11854

Total Subscribers:150

Foundational Models for State-of-the-Art Speech and Text Translation

speechbrain

by speechbrain

Total Stargazers:11818

Total Subscribers:139

A PyTorch-based Speech Toolkit

FluidVoice

by altic-dev

Total Stargazers:11462

Total Subscribers:50

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows pre-build available! A local Wispr Flow alternative. DM us on X exclusive model access! 😉 - https://x.com/fluidvoiceapp

ten-framework

by TEN-framework

Total Stargazers:11120

Total Subscribers:72

Open-source framework for conversational voice AI agents

moshi

by kyutai-labs

Total Stargazers:11066

Total Subscribers:106

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

moonshine

by moonshine-ai

Total Stargazers:11058

Total Subscribers:66

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

WhisperLiveKit

by QuentinFuxa

Total Stargazers:11028

Total Subscribers:61

Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.

spring-ai-alibaba

by alibaba

Total Stargazers:10839

Total Subscribers:114

Agentic AI Framework for Java Developers

Whisper

by Const-me

Total Stargazers:10659

Total Subscribers:111

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model

pyannote-audio

by pyannote

Total Stargazers:10538

Total Subscribers:81

Voice & Speech AI

Speech recognition, text-to-speech, voice cloning and real-time voice agents.

whisper

by openai

Robust Speech Recognition via Large-Scale Weak Supervision

GPT-SoVITS

by RVC-Boss

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Real-Time-Voice-Cloning

by CorentinJ

Clone a voice in 5 seconds to generate arbitrary speech in real-time

whisper.cpp

by ggml-org

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

voicebox

by jamiepine

The open-source AI voice studio. Clone, dictate, create.

airi

by moeru-ai

💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.

TTS

by coqui-ai

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

ChatTTS

by 2noise

A generative speech model for daily dialogue.

Retrieval-based-Voice-Conversion-WebUI

by RVC-Project

Easily train a good VC model with voice data <= 10 mins!

VoxCPM

by OpenBMB

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

MockingBird

by babysor

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

fish-speech

by fishaudio

SOTA Open Source TTS

Handy

by cjpais

A free, open source, and extensible speech-to-text application that works completely offline.

meetily

by Zackriya-Solutions

openai-agents-python

by openai

A lightweight, powerful framework for multi-agent workflows

chatterbox

by resemble-ai

SoTA open-source TTS

llamafile

by mozilla-ai

Distribute and run LLMs with a single file.

faster-whisper

by SYSTRAN

Faster Whisper transcription with CTranslate2

whisperX

by m-bain

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

index-tts

by index-tts

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

CosyVoice

by QwenAudio

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

VoiceStudio

by debpalash

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

buzz

by chidiwilliams

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

voice-changer

by w-okada

リアルタイムボイスチェンジャー Realtime Voice Changer

FunASR

by modelscope

Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

ebook2audiobook

by DrewThomasson

Generate audiobooks from e-books, voice cloning & 1158+ languages!

pydantic-ai