#1111th of 51 in VoiceFor voice, speech and music
fish-speech
Expressive multi-speaker text-to-speech models with voice cloning
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 33.4k
- License
- custom license
- Last commit
- Oct 2026
- Last release
- May 2025
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Fish Speech is the code and weights for Fish Audio's TTS models: Drama 3 (35B-A3B, 3B active per token) and S2-Pro (4B parameters). Both clone voices from reference audio, accept inline tags such as [whisper] and [angry], and share one command line and API server. Drama 3 adds infilling and multi-turn revision of earlier takes.
Who it is for: Developers who need self-hosted expressive TTS and voice cloning
Strengths
- Voice cloning from 10-30 seconds of reference audio (S2-Pro)
- Inline tags like [whisper], [excited], [laughing] control emotion and prosody
- Drama 3 can replace single words in audio and revise earlier takes
- S2-Pro reports RTF 0.195 and about 100 ms to first audio on one H200
Weaknesses
- Custom Fish Audio community license; S2-Pro weights under a separate research license
- Drama 3 is 35B total parameters; hardware requirements are not stated in the README
- Last tagged release is 2025-05-31, older than the current models
- README recommends SGLang-Omni or vLLM-Omni for efficient serving
What it needs
- Docker + Compose
- Needs PyTorch, Hugging Face model weights
- Models: Drama 3 (35B-A3B), S2-Pro (4B)
Also in Voice
See all 51| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 83 out of 100 |
| 2 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 80 out of 100 |
| 3 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 78 out of 100 |
| #4 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 71 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 71 out of 100 |