lenML/Speech-AI-Forge

🍦 Speech-AI-Forge is a project developed around TTS generation model, implementing an API Server and a Gradio-based WebUI.

61
/ 100
Established

Supports multiple cutting-edge TTS models (ChatTTS, CosyVoice, F5-TTS, FishSpeech, GPT-SoVITS) with integrated ASR, voice cloning, and audio enhancement through a unified FastAPI backend. Features advanced capabilities like long-text batch processing, SSML-based podcast generation, custom voice builders with seed blending, and real-time voice style/speed/pitch adjustment. Deployable via standalone API server, Docker containers, or interactive Gradio WebUI with comprehensive voice management hub.

1,386 stars. Actively maintained with 9 commits in the last 30 days.

No Package No Dependents
Maintenance 20 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

1,386

Forks

182

Language

Python

License

AGPL-3.0

Last pushed

Mar 06, 2026

Commits (30d)

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lenML/Speech-AI-Forge"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.