ttsfm 3.4.0a4

Text-to-Speech API Client with OpenAI compatibility

TTSFM - Text-to-Speech API Client

Language / 语言: English | 中文

Star History

Overview

TTSFM is a free, OpenAI-compatible text-to-speech stack powered by the openai.fm backend. It ships with Python clients, a REST API, and a web playground.

Installation

Python package

pip install ttsfm        # core client
pip install ttsfm[web]   # client + Flask web app

Docker image

TTSFM offers two Docker image variants to suit different needs:

Full variant (recommended)

docker run -p 8000:8000 dbcccc/ttsfm:latest

Includes ffmpeg for advanced features:

• ✅ MP3 auto-combine for long text
• ✅ Speed adjustment (0.25x - 4.0x)
• ✅ Additional audio formats (AAC, FLAC, OPUS)

Slim variant

docker run -p 8000:8000 dbcccc/ttsfm:v3.4.0-alpha1-slim

Minimal image without ffmpeg:

• ✅ Basic TTS (MP3/WAV)
• ✅ WAV auto-combine (simple concatenation)
• ❌ No MP3 auto-combine
• ❌ No speed adjustment
• ❌ No format conversion

The container exposes the web playground at http://localhost:8000 and an OpenAI-style endpoint at /v1/audio/speech.

Quick start

Python client

from ttsfm import TTSClient, AudioFormat, Voice

client = TTSClient()

# Basic usage
response = client.generate_speech(
    text="Hello from TTSFM!",
    voice=Voice.ALLOY,
    response_format=AudioFormat.MP3,
)
response.save_to_file("hello")  # -> hello.mp3

# With speed adjustment (requires ffmpeg)
response = client.generate_speech(
    text="This will be faster!",
    voice=Voice.NOVA,
    response_format=AudioFormat.MP3,
    speed=1.5,  # 1.5x speed (0.25 - 4.0)
)
response.save_to_file("fast")  # -> fast.mp3

CLI

ttsfm "Hello, world" --voice nova --format mp3 --output hello.mp3

REST API

curl -X POST http://localhost:8000/v1/audio/speech   -H "Content-Type: application/json"   -d '{"model":"gpt-4o-mini-tts","input":"Hello world!","voice":"alloy"}'   --output speech.mp3

Learn more

• Browse the full API reference and operational notes in the web documentation (or see ttsfm-web/templates/docs.html).
• Read the architecture overview for component diagrams.
• Contributions are welcome—see CONTRIBUTING.md for guidelines.

License

TTSFM is released under the MIT License.