Skip to content

F5-TTS is an open-source voice cloning tool from Shanghai Jiao Tong University with excellent results. The initial version only supported Chinese and English cloning, but the latest version v1 has been expanded to support multiple languages ​​such as French, Italian, Hindi, Japanese, Russian, Spanish, and Finnish.

This article mainly introduces how to install and launch F5-TTS using the official source code, and how to connect it with the pyVideotrans project. In addition, it will also introduce how to modify the source code to achieve calls within the local area network.

At the same time, due to limited energy, I will no longer maintain the previous personal integration package and API interface, but will uniformly use the official interface to connect with the pyVideotrans project. The limitation of the official interface is that it can only be called locally and cannot be called within the local area network. For the solution, please refer to the LAN usage section of this article.

Prerequisites

Your system must have Python 3.10 installed. Although versions 3.11/3.12 may theoretically work, they have not been tested in practice, so it is recommended to use version 3.10.

If Python is not installed yet:

Check if Python is installed:

  • Windows system: Press Win+R, enter cmd in the pop-up window and press Enter. Enter python --version in the opened black window. If 3.10.xx is displayed, it means it is installed; if it prompts "python is not an internal or external command", it means it is not installed or Python has not been added to the Path environment variable, and you need to reinstall it.
  • Mac system: Directly execute python3 --version in the terminal. If 3.10.x is output, it means it is installed; otherwise, you need to install it.

Download F5-TTS source code

First, create an empty folder in a suitable location. It is recommended to choose a non-system disk or a location that does not require special permissions, such as drive D. Avoid placing it in directories such as C:/Program Files (it is recommended that the location and folders at all levels use names composed of pure numbers or letters) to avoid potential problems. For example, D:/f5/v1 is a good location, while D:/开源 f5/f5 v1 with spaces and Chinese characters is not recommended.

This article takes installing F5-TTS in the D:/python/f5ttsnew folder of the Windows10 system as an example.

Open the website: https://github.com/SWivid/F5-TTS

As shown in the figure below, click to download the source code:

Download source code zip package

After the download is complete, unzip the package and copy all the files in the F5-TTS-main folder to the D:/python/f5ttsnew folder, as shown in the figure below:

Inside the F5-TTS-main folder in the zip package

Copy to f5ttsnew

Create a virtual environment

It is strongly recommended to create a virtual environment unless there are no other Python or AI projects on your computer. Virtual environments can effectively avoid many potential errors.

Enter cmd in the address bar of the newly created folder D:/python/f5ttsnew and press Enter (Mac system, please use the terminal to enter the folder).

Execute the following command to create a virtual environment: python -m venv venv. After execution, a folder named venv will be added to the folder.

Next, activate the virtual environment (note the spaces and dot symbols):

  • Windows system: .\venv\scripts\activate
  • Mac system: . ./venv/bin/activate

After the virtual environment is activated, the prompt before the command line will add the word (venv). Please be sure to ensure that all subsequent operations are performed in this virtual environment, and check whether the command line prompt has (venv) before each operation.

(venv) in front of the command line means activation

Install dependencies

In the terminal where the virtual environment has been activated, continue to enter the following command (note the spaces and dot symbols):

pip install -e .

Wait for the installation to complete. If CUDA acceleration is required, continue to execute the following command (this is one line of command, do not wrap):

# Install pytorch with your CUDA version, e.g.
pip install torch==2.4.0+cu124 torchaudio==2.4.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124

Configure scientific internet access environment

Important reminder: F5-TTS needs to download models online from the huggingface.co website. Since this website has been blocked in China and cannot be connected directly, you must configure a scientific internet access environment and enable global or system proxy before starting it.

If the VPN tool you are using provides an HTTP port (as shown in the figure below):

Check whether the science software provides a port

Please enter the following command in the terminal to set the proxy:

  • Windows system: set https_proxy=http://127.0.0.1:10808 (Please replace the port number with the port you actually use)
  • Mac system: https_proxy=http://127.0.0.1:10808 (Please replace the port number with the port you actually use)

You can also directly modify the code to set the proxy, avoiding manual input in the terminal each time. Open the F5-TTS root directory/src/f5_tts/infer/infer_gradio.py file and add the following code at the top of the file:

python
import os
os.environ['https_proxy']='http://127.0.0.1:10808' # Fill in according to your actual proxy address

Start the WebUI interface

After configuring the scientific internet access environment, enter the following command in the terminal to start the WebUI:

f5-tts_infer-gradio

When starting for the first time, the program will automatically download the model. The process may be slow, please be patient. When starting later, the program may still connect to huggingface.co for detection. It is recommended to keep the proxy turned on to avoid errors.

After the startup is successful, the terminal will display the IP address and port number, as shown in the figure below:

Successful startup when IP and port are displayed, the first time is very slow

Open the displayed address in the browser, the default is http://127.0.0.1:7860.

webui interface

Connect to pyVideoTrans's API

To use F5-TTS in video translation software, you need to start F5-TTS first and keep the terminal window open.

Then, open the video translation software, and select "TTS Settings" -> "F5-TTS API" in the menu, and fill in the startup address of F5-TTS, the default is http://127.0.0.1:7860. If your startup address is not the default address, please fill it in according to the actual address.

In the "Reference Audio" column, fill in the following content:

Audio file name to use#The corresponding text in the audio file

Note: Please place the reference audio file in the f5-tts folder under the root directory of the pyVideotrans project. If the folder does not exist, please create it manually. For example, you can name the reference audio file nverguo.wav.

Put the reference audio into the f5-tts folder in the pyVideotrans software, don't get it wrong

The following is an example:

Reference audio and text in reference audio

Re-recognize?: By default, the reference audio (the subtitles recognized during cloning) will be sent to F5-TTS to avoid F5-TTS starting whisper to do speech recognition, saving time and improving efficiency. However, sometimes you may want F5-TTS to re-recognize, which can improve cloning quality to a certain extent. At this time, you can check the check box, but note that if you check it for the first time, F5-TTS will download the openai-whisper-v3 model online from huggingface.co, please make sure you have scientific internet access.

Solve LAN problem

If your F5-TTS is deployed on another computer in the local area network, you need to modify the F5-TTS code to support LAN access.

Open the F5-TTS project directory/src/f5_tts/infer/infer_gradio.py file and add the following code below line 16:

python
# Add LAN start
import os
from pathlib import Path

ROOT=Path(os.getcwd()).as_posix()
TMP=f'{ROOT}/tmp'
Path(TMP).mkdir(exist_ok=True)
os.environ['GRADIO_TEMP_DIR']=TMP
gr.set_static_paths(paths=[TMP,tempfile.gettempdir()])
print(TMP)

## Add LAN end

Schematic diagram of the code addition location:Note the location where the code is added

After saving the changes, restart F5-TTS. Then fill in the IP address and port number after F5-TTS is started in pyVideotrans, such as http://192.168.0.12:7860.

Add other languages

If you need to use models in other languages, you also need to modify the F5-TTS project directory/src/f5_tts/infer/infer_gradio.py file.

Find the code around line 59:

python
DEFAULT_TTS_MODEL_CFG = [
    "hf://SWivid/F5-TTS/F5TTS_v1_Base/model_1250000.safetensors",
    "hf://SWivid/F5-TTS/F5TTS_v1_Base/vocab.txt",
    json.dumps(dict(dim=1024, depth=22, heads=16, ff_mult=2, text_dim=512, conv_layers=4)),
]

Code location diagram:

By default, the official Chinese and English models are configured here. If you need to use models in other languages, please modify them according to the following instructions. After the modification is completed, you need to restart F5-TTS and make sure that the scientific internet access environment is configured so that the program can download the new language model online. After the download is successful, first clone a tone through WebUI for testing, and then use it through pyVideoTrans.

Important reminder: Before using it, please make sure that the dubbing text language in pyVideoTrans is consistent with the model language selected in F5-TTS.

The following are the configuration information for each language model:

  1. French:

    python
    DEFAULT_TTS_MODEL_CFG = [
        "hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/model_last_reduced.pt",
        "hf://RASPIAUDIO/F5-French-MixedSpeakers-reduced/vocab.txt",
        json.dumps({"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1}),
    ]
  2. Hindi:

    python
    DEFAULT_TTS_MODEL_CFG = [
        "hf://SPRINGLab/F5-Hindi-24KHz/model_2500000.safetensors",
        "hf://SPRINGLab/F5-Hindi-24KHz/vocab.txt",
        json.dumps({"dim": 768, "depth": 18, "heads": 12, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1})
    ]
  3. Italian:

    python
    DEFAULT_TTS_MODEL_CFG = [
        "hf://alien79/F5-TTS-italian/model_159600.safetensors",
        "hf://alien79/F5-TTS-italian/vocab.txt",
        json.dumps({"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1})
    ]
  4. Japanese:

    python
    DEFAULT_TTS_MODEL_CFG = [
        "hf://Jmica/F5TTS/JA_25498980/model_25498980.pt",
        "hf://Jmica/F5TTS/JA_25498980/vocab_updated.txt",
        json.dumps({"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1})
    ]
  5. Russian:

    python
    DEFAULT_TTS_MODEL_CFG = [
        "hf://hotstone228/F5-TTS-Russian/model_last.safetensors",
        "hf://hotstone228/F5-TTS-Russian/vocab.txt",
        json.dumps({"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1})
    ]
  6. Spanish:

    python
    DEFAULT_TTS_MODEL_CFG = [
        "hf://jpgallegoar/F5-Spanish/model_last.safetensors",
        "hf://jpgallegoar/F5-Spanish/vocab.txt",
        json.dumps({"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "conv_layers": 4})
    ]
  7. Finnish:

    python
       DEFAULT_TTS_MODEL_CFG = [
        "hf://AsmoKoskinen/F5-TTS_Finnish_Model/model_common_voice_fi_vox_populi_fi_20241206.safetensors",
        "hf://AsmoKoskinen/F5-TTS_Finnish_Model/vocab.txt",
        json.dumps({"dim": 1024, "depth": 22, "heads": 16, "ff_mult": 2, "text_dim": 512, "text_mask_padding": False, "conv_layers": 4, "pe_attn_head": 1})]

You can follow the official updates and use similar methods to add other languages. Address: https://github.com/SWivid/F5-TTS/blob/main/src/f5_tts/infer/SHARED.md

Common Errors and Precautions

  1. During API usage, you can close the WebUI interface in the browser, but you cannot close the terminal window that started F5-TTS.

    This interface cannot be closed, otherwise the api cannot be called

  2. Can I dynamically switch models in F5-TTS? No. You need to manually modify the code as described above, and then restart the WebUI.

  3. Frequent occurrence of this type of error

    raise ConnectTimeout(e, request=request)
requests.exceptions.ConnectTimeout: (MaxRetryError("HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /SWivid/F5-TTS/resolve/main/F5TTS_v1_Base/vocab.txt (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000002174796DF60>, 'Connection to huggingface.co timed out. (connect timeout=10)'))"), '(Request ID: 0458b571-90ab-4edd-ae59-b93bd603cdd0)')

Proxy issue, please use scientific internet access and use a smooth proxy. Refer to the above to configure the scientific internet access environment

  1. How to prevent connecting to huggingface.co every time?

Please make sure you have successfully cloned at least once and the model has been downloaded Open F5-TTS root directory/src/f5_tts/infer/utils_infer.py

Search snapshot_download and find this line of code as shown in the picture

Modified to

local_path = snapshot_download(repo_id="nvidia/bigvgan_v2_24khz_100band_256x", cache_dir=hf_cache_dir,local_files_only=True)

Then search for hf_hub_download and find the 2 lines of code shown in the figure

Modified to

config_path = hf_hub_download(repo_id=repo_id, cache_dir=hf_cache_dir, filename="config.yaml",local_files_only=True)
            model_path = hf_hub_download(repo_id=repo_id, cache_dir=hf_cache_dir, filename="pytorch_model.bin",local_files_only=True)

Actually, the new parameter ,local_files_only=True is added to the place where these 3 lines of code are called. Please make sure the model has been downloaded locally, otherwise it will report a model not found error

  1. F5-TTS is deployed normally, but the test in pyVideotrans returns {detail:"Not found"}
    • Check whether other AI projects are occupying the port. Generally, AI projects with interfaces use the gradio interface, which also defaults to 7860. Close the others and restart F5-TTS
    • If pyVideotrans is deployed from source code, please execute pip install --upgrade gradio_client and then try again
    • Restart F5-TTS, use the command f5-tts_infer-gradio --api to start