F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching

F5-TTS: Diffusion Transformer with ConvNeXt V2, faster trained and inference.

E2 TTS: Flat-UNet Transformer, closest reproduction from paper.

Sway Sampling: Inference-time flow step sampling strategy, greatly improves performance

Thanks to all the contributors !

News

• 2025/03/12: 🔥 F5-TTS v1 base model with better training and inference performance. Few demo.
• 2024/10/08: F5-TTS & E2 TTS base models on 🤗 Hugging Face, 🤖 Model Scope, 🟣 Wisemodel.

Installation

Create a separate environment if needed

# Create a conda env with python_version>=3.10  (you could also use virtualenv)
conda create -n f5-tts python=3.11
conda activate f5-tts

# Install FFmpeg if you haven't yet
conda install ffmpeg

Install PyTorch with matched device

NVIDIA GPU

# Install pytorch with your CUDA version, e.g.
pip install torch==2.8.0+cu128 torchaudio==2.8.0+cu128 --extra-index-url https://download.pytorch.org/whl/cu128

# And also possible previous versions, e.g.
pip install torch==2.4.0+cu124 torchaudio==2.4.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124
# etc.

AMD GPU

# Install pytorch with your ROCm version (Linux only), e.g.
pip install torch==2.5.1+rocm6.2 torchaudio==2.5.1+rocm6.2 --extra-index-url https://download.pytorch.org/whl/rocm6.2

Intel GPU

# Install pytorch with your XPU version, e.g.
# Intel® Deep Learning Essentials or Intel® oneAPI Base Toolkit must be installed
pip install torch torchaudio --index-url https://download.pytorch.org/whl/test/xpu

# Intel GPU support is also available through IPEX (Intel® Extension for PyTorch)
# IPEX does not require the Intel® Deep Learning Essentials or Intel® oneAPI Base Toolkit
# See: https://pytorch-extension.intel.com/installation?request=platform

Apple Silicon

# Install the stable pytorch, e.g.
pip install torch torchaudio

Then you can choose one from below:

1. As a pip package (if just for inference)

pip install f5-tts

2. Local editable (if also do training, finetuning)

git clone https://github.com/SWivid/F5-TTS.git
cd F5-TTS
# git submodule update --init --recursive  # (optional, if use bigvgan as vocoder)
pip install -e .

Docker usage also available

# Build from Dockerfile
docker build -t f5tts:v1 .

# Run from GitHub Container Registry
docker container run --rm -it --gpus=all --mount 'type=volume,source=f5-tts,target=/root/.cache/huggingface/hub/' -p 7860:7860 ghcr.io/swivid/f5-tts:main

# Quickstart if you want to just run the web interface (not CLI)
docker container run --rm -it --gpus=all --mount 'type=volume,source=f5-tts,target=/root/.cache/huggingface/hub/' -p 7860:7860 ghcr.io/swivid/f5-tts:main f5-tts_infer-gradio --host 0.0.0.0

Runtime

Deployment solution with Triton and TensorRT-LLM.

Benchmark Results

Decoding on a single L20 GPU, using 26 different prompt_audio & target_text pairs, 16 NFE.

Model	Concurrency	Avg Latency	RTF	Mode
F5-TTS Base (Vocos)	2	253 ms	0.0394	Client-Server
F5-TTS Base (Vocos)	1 (Batch_size)	-	0.0402	Offline TRT-LLM
F5-TTS Base (Vocos)	1 (Batch_size)	-	0.1467	Offline Pytorch

See detailed instructions for more information.

Inference

• In order to achieve desired performance, take a moment to read detailed guidance.
• By properly searching the keywords of problem encountered, issues are very helpful.

1. Gradio App

Currently supported features:

• Basic TTS with Chunk Inference
• Multi-Style / Multi-Speaker Generation
• Voice Chat powered by Qwen2.5-3B-Instruct
• Custom inference with more language support

# Launch a Gradio app (web interface)
f5-tts_infer-gradio

# Specify the port/host
f5-tts_infer-gradio --port 7860 --host 0.0.0.0

# Launch a share link
f5-tts_infer-gradio --share

NVIDIA device docker compose file example

services:
  f5-tts:
    image: ghcr.io/swivid/f5-tts:main
    ports:
      - "7860:7860"
    environment:
      GRADIO_SERVER_PORT: 7860
    entrypoint: ["f5-tts_infer-gradio", "--port", "7860", "--host", "0.0.0.0"]
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]

volumes:
  f5-tts:
    driver: local

2. CLI Inference

# Run with flags
# Leave --ref_text "" will have ASR model transcribe (extra GPU memory usage)
f5-tts_infer-cli --model F5TTS_v1_Base \
--ref_audio "provide_prompt_wav_path_here.wav" \
--ref_text "The content, subtitle or transcription of reference audio." \
--gen_text "Some text you want TTS model generate for you."

# Run with default setting. src/f5_tts/infer/examples/basic/basic.toml
f5-tts_infer-cli
# Or with your own .toml file
f5-tts_infer-cli -c custom.toml

# Multi voice. See src/f5_tts/infer/README.md
f5-tts_infer-cli -c src/f5_tts/infer/examples/multi/story.toml

Training

1. With Hugging Face Accelerate

Refer to training & finetuning guidance for best practice.

2. With Gradio App

# Quick start with Gradio web interface
f5-tts_finetune-gradio

Read training & finetuning guidance for more instructions.

Evaluation

Development

Use pre-commit to ensure code quality (will run linters and formatters automatically):

pip install pre-commit
pre-commit install

When making a pull request, before each commit, run:

pre-commit run --all-files

Note: Some model components have linting exceptions for E722 to accommodate tensor notation.

Acknowledgements

• E2-TTS brilliant work, simple and effective
• Emilia, WenetSpeech4TTS, LibriTTS, LJSpeech valuable datasets
• lucidrains initial CFM structure with also bfs18 for discussion
• SD3 & Hugging Face diffusers DiT and MMDiT code structure
• torchdiffeq as ODE solver, Vocos and BigVGAN as vocoder
• FunASR, faster-whisper, UniSpeech, SpeechMOS for evaluation tools
• ctc-forced-aligner for speech edit test
• mrfakename huggingface space demo ~
• f5-tts-mlx Implementation with MLX framework by Lucas Newman
• F5-TTS-ONNX ONNX Runtime version by DakeQQ
• Yuekai Zhang Triton and TensorRT-LLM support ~

Citation

If our work and codebase is useful for you, please cite as:

@article{chen-etal-2024-f5tts,
      title={F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching}, 
      author={Yushen Chen and Zhikang Niu and Ziyang Ma and Keqi Deng and Chunhui Wang and Jian Zhao and Kai Yu and Xie Chen},
      journal={arXiv preprint arXiv:2410.06885},
      year={2024},
}

License

Our code is released under MIT License. The pre-trained models are licensed under the CC-BY-NC license due to the training data Emilia, which is an in-the-wild dataset. Sorry for any inconvenience this may cause.