VoxCPM1.5

Word count

200 words

Reading time

2 minutes

VoxCPM1.5 Leading word-segmentation-free TTS technology enables highly expressive, context-aware speech generation. Supports both Chinese and English, and efficiently achieves zero-sample voice cloning.

Main Interface

`

Launch Methods

• Launch via URL

http://127.0.0.1:8000/launcher?project=voxcpm

• Launch via Command

uv run cli.py install -n voxcpm -p 8016 --start

• Native Launch (API Only)

uv run app.py

Output Logs

Python 3.11.11
Using extensions/voxcpm/.venv/scripts/python.exe
Checked 179 packages in 6ms
All installed packages are compatible
Audited 42 packages in 14ms
...
extensions/voxcpm/.venv/scripts/python.exe app_v1_5.py --host 0.0.0.0 --port 8016
2025-12-29 18:51:16.242 | INFO     | src.utils.cblauncher:start:450 - ✅ voxcpm has started (PID: 12552)
funasr version: 1.2.9.
Downloading Model from https://www.modelscope.cn to directory: D:\Projects\fast\fast-creator\models\modelscope\hub\models\iic\SenseVoiceSmall
WARNING:root:trust_remote_code: False
* Running on local URL:  http://0.0.0.0:8016
* To create a public link, set `share=True` in `launch()`.

Configuration Parameters

webapp/extensions/voxcpm/data/config.json

{
    "cfg_value_input": 2,
    "inference_timesteps_input": 10,
    "do_normalize": false,
    "denoise": false
}

Notes

• request: inference request parameters

• models: custom model configuration

• In the dubbing module, you can fill in local or remote addresses to enable batch speech synthesis, for example:

  • Local access: http://127.0.0.1:8016
  • Remote access: https://xxx.gradio.live、https://xxx.ngrok-free.app、https://xxx.loca.lt
  • Your own public IP or domain