BigHugger
GH Repository · lenML

Speech-AI-Forge

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

stars
1,419
30-day movement
starts with the next reading
Related entries
60
Connections
1
fireredttswhisperfireredsttcosy-voiceagent-appasrcosyvoicenodechatttsttschattts-forgellamassmlagentdockergptpythonllmtext-to-speechcolabchineseenglishPython

Speech-AI-Forge is a Python project built around TTS generation models, exposing them through an API Server and a Gradio-based WebUI. Its topics reference multiple TTS engines (ChatTTS, CosyVoice, Fish-Speech, FireRedTTS) plus ASR/STT models like Whisper.

It gives you a ready-made server and web interface for text-to-speech generation without building the serving layer yourself.

Use it to

  • Run a TTS API server locally
  • Generate speech through the Gradio WebUI
  • Experiment with multiple TTS models via one interface
  • Deploy TTS in a Colab notebook
  • Pair speech generation with LLM/agent workflows

For Developers integrating text-to-speech into apps or agents

Role
agent-app
Language
Python
Licence
AGPL-3.0
Forks
187
Open issues
76
Last push
2026-05-21
Latest release
portable_v0.7 · 2026-02-02
topicstext-to-speechttsapi-servergradioagentasr