This is a webui and api project for the kokoro TTS project, supporting voice synthesis in 8 languages including Chinese, English, Japanese, French, Italian, Portuguese, Spanish, and Hindi.

Project address: https://github.com/jianchang512/kokoro-uiapi

Web Interface

Default UI address after startup: http://127.0.0.1:5066

• Supports voice synthesis for text and SRT subtitles
• Supports online preview and download
• Supports subtitle alignment

Installation Methods

Windows

For Windows 10/11, you can directly download the integration package and double-click start.bat to start. For GPU acceleration, ensure you have an NVIDIA graphics card and install CUDA 12.

Baidu Netdisk download address: https://pan.baidu.com/s/1jTB84E3-gaLqFrl32f4sDw?pwd=xnwp

GitHub download (without models, requires VPN for online download): https://github.com/jianchang512/kokoro-uiapi/releases/download/v0.1/kokoro-uiapi-noModels-v0.2.7z

Linux/MacOS

First, ensure the system has Python 3.8+ installed; 3.10-3.11 is recommended.

On Linux, use apt install ffmpeg or yum install ffmpeg to pre-install ffmpeg.

On MacOS, use brew install ffmpeg to install ffmpeg.

1. Clone the source code: git clone https://github.com/jianchang512/kokoro-uiapi
2. Create and activate a virtual environment:

   cd kokoro-uiapi
   python3 -m venv venv
   . venv/bin/activate

3. Install dependencies: pip3 install -r requirements.txt
4. Start: python3 app.py

Using in pyVideoTrans

1. First, start this project: double-click start.bat for the Windows integration package, or run python3 app.py for source installation.
2. Upgrade pyVideoTrans to v3.48+, open the menu -- TTS Settings -- Kokoro TTS -- fill in the HTTP address as http://127.0.0.1:5066.

OpenAI API Compatibility

The API is compatible with OpenAI TTS.

Default API address after startup: http://127.0.0.1:5066/v1/audio/speech

Request method: POST Request data: application/json

{
    input: text to synthesize,
    voice: voice role,
    speed: speech rate, default 1.0
}

Returns MP3 audio data on success.

OpenAI SDK Usage Example

from openai import OpenAI
client = OpenAI(
    api_key='123456',
    base_url='http://127.0.0.1:5066/v1'
)

try:
    response = client.audio.speech.create(
        model='tts-1',
        input='Hello there, dear friends',
        voice='zf_xiaobei',
        response_format='mp3',
        speed=1.0
    )
    with open('./test_openai.mp3', 'wb') as f:
        f.write(response.content)
    print("MP3 file saved successfully to test_openai.mp3")
except Exception as e:
    print(f"An error occurred: {e}")

Voice Role List

English voice roles:

af_alloy
af_aoede
af_bella
af_jessica
af_kore
af_nicole
af_nova
af_river
af_sarah
af_sky
am_adam
am_echo
am_eric
am_fenrir
am_liam
am_michael
am_onyx
am_puck
am_santa
bf_alice
bf_emma
bf_isabella
bf_lily
bm_daniel
bm_fable
bm_george
bm_lewis

Chinese voice roles:

zf_xiaobei
zf_xiaoni
zf_xiaoxiao
zf_xiaoyi
zm_yunjian
zm_yunxi
zm_yunxia
zm_yunyang

Japanese voice roles:

jf_alpha
jf_gongitsune
jf_nezumi
jf_tebukuro
jm_kumo

French voice role: ff_siwis

Italian voice roles: if_sara, im_nicola

Hindi voice roles: hf_alpha, hf_beta, hm_omega, hm_psi

Spanish voice roles: ef_dora, em_alex, em_santa

Portuguese voice roles: pf_dora, pm_alex, pm_santa

Proxy VPN

For source code deployment, voice model pt files need to be downloaded from huggingface.co. Set up a global or system proxy in advance to ensure access.

Alternatively, download the models in advance and extract them to the directory where app.py is located.

Model download address: https://github.com/jianchang512/kokoro-uiapi/releases/download/v0.1/moxing--jieya--dao--app.py--mulu.7z

Credit

• Kokoro-82M