lenML/Speech-AI-Forge

Health v2 · maintenance only

Adoption not part of the score

1416 stars · 189 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Speech-AI-Forge is a Python project built around multiple TTS generation models (ChatTTS, CosyVoice, Fish-Speech, Index-TTS, F5-TTS, FireRedTTS, and more) that provides both an API server and a Gradio-based WebUI. It also supports ASR/STT via Whisper and SenseVoice, SSML, and cloud TTS backends like MiniMax.

Use cases

• generate speech from text with multiple tts models
• self-host a text-to-speech api server
• clone a voice for tts synthesis
• transcribe audio to text with whisper or sensevoice
• run a gradio webui for text-to-speech
• use ssml to control speech synthesis
• try tts models in colab without installing

When to choose

• you want one self-hosted server exposing many open-source TTS models behind a unified API
• you need both a WebUI for experimentation and an API for integration
• you want SSML support and voice cloning across multiple TTS engines
• you need Chinese and English speech synthesis

When to avoid

• you need a lightweight production TTS service with a single optimized model
• you require a permissively licensed dependency since it is AGPL-3.0
• you need real-time low-latency streaming TTS at scale
• you only want cloud TTS without local model support

Facets

application · maturity active

tts speech-recognition http-server llm-inference api-framework speech-processing artificial-intelligence python windows cross-platform text-to-speech gradio-webui chattts cosyvoice fish-speech ssml voice-cloning asr whisper colab natural-language-processing audio docker web-server gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="lenML/Speech-AI-Forge")