Python Package

Free Text-to-Speech for Python

Generate high-quality speech from text using the free openai.fm service. No API keys, no registration - just install and start creating audio.

Try Demo Documentation GitHub

Key Features

Simple, free, and powerful text-to-speech for Python developers.

Completely Free

No API keys or registration required. Uses the free openai.fm service.

OpenAI Compatible v3.2.8

Drop-in replacement for OpenAI's TTS API with auto-combine for long text.

Async & Sync

Both asyncio and synchronous clients for maximum flexibility.

11 Voices & 6 Audio Formats

All OpenAI-compatible voices available for different use cases. MP3, WAV, OPUS, AAC, FLAC, and PCM support for any application.

Quick Start

Generate high-quality speech from text using the free openai.fm service. No API keys, no registration - just install and start creating audio.

Installation

pip install ttsfm

Requires Python 3.8+

Basic Usage

from ttsfm import TTSClient, Voice, AudioFormat

client = TTSClient()
response = client.generate_speech(
    text="Hello, world!",
    voice=Voice.ALLOY,
    response_format=AudioFormat.MP3
)
response.save_to_file("hello")

No API keys required

Try Demo Documentation