fishaudio/fish-speech
SOTA Open Source TTS
This project helps creators, marketers, and content producers generate incredibly natural and expressive voices from text. You input written text, optionally with emotion or prosody tags like "[whisper]" or "[excited]", and it outputs realistic spoken audio in over 80 languages. This is for anyone who needs high-quality, emotionally rich synthetic speech for voiceovers, virtual assistants, or educational content.
26,613 stars. Actively maintained with 18 commits in the last 30 days.
Use this if you need to transform text into highly realistic, emotionally nuanced speech in multiple languages with fine-grained control over vocal delivery.
Not ideal if you need a simple, quick text-to-speech solution without needing advanced emotional control or multilingual support.
Stars
26,613
Forks
2,237
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/fishaudio/fish-speech"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related tools
Blaizzy/mlx-audio
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's...
lenML/Speech-AI-Forge
🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server...
sidharthrajaram/StyleTTS2
🐍 🤖 Pip installable package for StyleTTS 2 human-level text-to-speech and voice cloning
mlalma/kokoro-ios
Kokoro TTS for iOS and macOSX
mlalma/KokoroTestApp
Test application for Kokoro TTS model