VoxCPM-0.5B A Small but Excellent One-Click Voice Cloning Integration Package

VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and Realistic Voice Cloning

How to Use

Download and extract the package.
Double-click 双击启动.bat (Double-click to start.bat). On the first launch, it will download the SenseVoiceSmall model from modelscope.cn, which is used to transcribe the reference audio into corresponding text.

After successful startup, the operation interface will automatically open in your browser. If it doesn't open, please manually visit http://127.0.0.1:7860 in your browser.

Interface during startup Starting Up

If the bottom of the final window displays as shown below, it indicates success.

If an Error: message appears at the end as shown below, it has failed. Please close the window and reopen it.

Upon success, the address http://127.0.0.1:7860 will automatically open in your browser.

Upload a 3-10 second reference audio clip to clone its voice timbre. After uploading, the corresponding text content will be automatically recognized and generated. You can also modify it manually. Then, enter the text you want to synthesize into speech.

The integration package includes the model, but it may still check for model updates. If you encounter a network connection failure during use, with an error message containing a string similar to HTTPConnection, and you do not have access to scientific internet tools, you can right-click to edit 双击启动.bat (Double-click to start.bat). Delete the rem in front of the line rem set HF_ENDPOINT=https://hf-mirror.com, then save the file and double-click to start it again.
If you have access to scientific internet tools and know the proxy port used by your tool, you can skip the previous step. Instead, delete the rem in front of the line rem set https_proxy=http://127.0.0.1:10808 and change the port 10808 to your proxy port. Save the file, restart, and this will ensure a more stable connection, reducing the likelihood of connection errors.