Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
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.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
YuE2: frontier music generation with symbolic planning, zero-shot covers, and agentic music editing.
Faster Whisper transcription with CTranslate2
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)