VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
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.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.
SOTA Open Source TTS
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
Easily train a good VC model with voice data <= 10 mins!
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.