---
id: f5-tts
version: "1.1.22"
license: MIT License
license_treatment: permissive
maintenance: active
---

# f5-tts — F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

License: permissive · Maintenance: active · Downloads: 104.8K/mo

## What it is and what it does

F5-TTS is a neural text-to-speech system that converts written text into natural-sounding speech using diffusion transformers with flow matching. It accepts a reference audio clip and its transcription to learn a speaker's voice characteristics, then generates new speech in that voice for arbitrary text input. The package includes both a Diffusion Transformer variant (F5-TTS) optimized for speed and a Flat-UNet variant (E2-TTS) for closer paper reproduction.

The package ships with a Gradio web interface for interactive use, a command-line tool for batch inference, and a Python API for programmatic access. It supports multi-speaker synthesis, style transfer, and voice chat features. Inference is accelerated via PyTorch on GPU hardware; the fact sheet documents deployment via Triton and TensorRT-LLM for production use. Training and fine-tuning are supported through Hugging Face Accelerate.

Use it for:

- Generate natural-sounding narration or audiobook content from text while preserving a specific speaker's voice characteristics.
- Clone a speaker's voice from a short reference clip and synthesize new dialogue in that voice for video dubbing or animation.
- Build a voice chat application that responds with synthesized speech matching a user's preferred speaker style.
- Fine-tune the base model on custom speech data to improve synthesis quality for specialized domains or accented speech.
- Deploy a production TTS service using the documented Triton runtime for low-latency, high-concurrency inference.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

F5-TTS generates natural-sounding speech from text using flow-matching diffusion transformers, with support for multi-speaker and multi-style synthesis from reference audio.

Yes, if you have GPU hardware and need flexible, high-quality speech synthesis with voice cloning. The package is actively maintained, has no known vulnerabilities, and offers both interactive and programmatic interfaces. Install friction is low. However, it is not suitable for CPU-only environments due to inference speed, and requires careful PyTorch setup for your specific GPU architecture (NVIDIA, AMD, Intel, or Apple Silicon).

## Install

pip install f5-tts
uv add f5-tts
poetry add f5-tts

## Installing f5-tts

Before you install: Low install friction with a pure Python wheel. Active maintenance with recent updates (22 days since last release). Requires 28 runtime dependencies including PyTorch, torchaudio, and transformers; GPU support is strongly recommended for practical inference speed.

License in practice: MIT License permits unrestricted use, modification, and distribution with minimal restrictions—suitable for both research and commercial applications.

Quickstart:

pip install f5-tts

from f5_tts.infer.api import F5TTS

model = F5TTS()
audio = model.infer(
    ref_audio='prompt.wav',
    ref_text='The content of reference audio.',
    gen_text='Text to synthesize.'
)

Requires PyTorch with GPU support (NVIDIA, AMD, Intel, or Apple Silicon) for practical inference speed; CPU-only inference will be very slow. Minimum Python 3.10 recommended.

Verify before relying:

- Whether the package supports real-time or streaming inference beyond the documented batch/offline modes.
- Specific language support beyond the mentioned Chinese-English bilingual base model.
- Memory requirements for different model sizes and batch configurations.
- Whether fine-tuning is practical on consumer hardware or requires enterprise-grade GPUs.

## Package facts

- License: MIT License (permissive)
- Python support: unspecified
- Install friction: low
- Maintenance: active
- Downloads: 104.8K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

text to speech synthesis, voice cloning from audio, multi-speaker TTS, neural speech generation, flow matching TTS, diffusion transformer speech, style transfer speech synthesis, speech-synthesis, voice-cloning, diffusion-models

[View on SkillFed](https://skillfed.io/packages/f5-tts) · [View on PyPI](https://pypi.org/project/f5-tts/)