Discover great AI tools
📢 NoticeWebsite launched:DeepToSeek AI tools directory is live. Submit great tools and get featured!
Curated on GitHub

Open Source Radar: Audio

Scanning GitHub for open-source AI projects that are actually worth running: self-hostable, forkable, with a clear license. Star counts and languages are verified against each repository.

148Projects
8.8mTotal stars
10Categories
21 open-source projects
agents livekit/agents

A framework for building realtime voice AI agents 🤖🎙️📹

agentsai
15.3k Python Apache-2.0Updated 2d ago
sherpa-onnx k2-fsa/sherpa-onnx

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

aarch64android
16k C++ Apache-2.0Updated 2d ago
Speech NVIDIA-NeMo/Speech

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)

asrdeeplearning
18.8k Python Apache-2.0Updated 2d ago
VoiceStudio debpalash/VoiceStudio

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

aiaudiobook
113.1k Python AGPL-3.0Updated 2d ago
FunASR modelscope/FunASR

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

asraudio
21.1k Python MITUpdated 3d ago
buzz chidiwilliams/buzz

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

whisper
22.9k Python MITUpdated 4d ago
fish-speech fishaudio/fish-speech

SOTA Open Source TTS

llamatransformer
33.8k Python Updated 6d ago
whisperX m-bain/whisperX

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

asrspeech
25.4k Python BSD-2-ClauseUpdated 7d ago
faster-whisper SYSTRAN/faster-whisper

Faster Whisper transcription with CTranslate2

deep-learninginference
26.8k Python MITUpdated 8d ago
YuE multimodal-art-projection/YuE

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

aiaudio-generation
13.6k Python Apache-2.0Updated 19d ago
voicebox jamiepine/voicebox

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

aicuda
60.9k Python MITUpdated 1mo ago
whisper openai/whisper

Robust Speech Recognition via Large-Scale Weak Supervision

113.1k Python MITUpdated 2mo ago
Retrieval-based-Voice-Conversion-WebUI RVC-Project/Retrieval-based-Voice-Conversion-WebUI

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

audio-analysischange
39.3k Python MITUpdated 3mo ago
CosyVoice QwenAudio/CosyVoice

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

audio-generationcantonese
24.4k Python Apache-2.0Updated 5mo ago
audiocraft facebookresearch/audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

23.9k Jupyter Notebook MITUpdated 8mo ago
kokoro hexgrad/kokoro

https://hf.co/hexgrad/Kokoro-82M

10.2k JavaScript Apache-2.0Updated 2025-08
I
index-tts index-tts/index-tts

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

bigvgancross-lingual
25.2k Python Apache-2.0
C
ChatTTS 2noise/ChatTTS

A generative speech model for daily dialogue.

chatchattts
40k Python AGPL-3.0
V
VoxCPM OpenBMB/VoxCPM

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

audiomultilingual
42.6k Python Apache-2.0
T
TTS coqui-ai/TTS

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

deep-learningmulti-speaker-tts
46.2k Python MPL-2.0
G
GPT-SoVITS RVC-Boss/GPT-SoVITS

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

text-to-speechtts
65.3k Python MIT