Index-TTS2

Word count

397 words

Reading time

3 minutes

Index-TTS2 It is a powerful autoregressive zero-shot text-to-speech system that enables unprecedented control over speech generation, featuring advanced emotional expression, precise duration control, and instant voice cloning capabilities.

Main Interface

Launch Methods

• Launch via URL

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

• Launch via Command

uv run cli.py install -n index_tts -p 8014 --start

• Native Launch

uv run webui.py --host 0.0.0.0 --port 8014 --fp16 --deepspeed

Output Logs

Python 3.10.19
Using extensions/index_tts/.venv/scripts/python.exe
Checked 162 packages in 4ms
All installed packages are compatible
Resolved 190 packages in 0.63ms
...

git 2.51.0
Using D:/Develop Files/Git/cmd/git.EXE
Updated Git hooks.
Git LFS initialized.
 _   .-')                _ .-') _     ('-.             .-')                              _ (`-.    ('-.
( '.( OO )_             ( (  OO) )  _(  OO)           ( OO ).                           ( (OO  ) _(  OO)
 ,--.   ,--.).-'),-----. \     .'_ (,------.,--.     (_)---\_)   .-----.  .-'),-----.  _.`     \(,------.
 |   `.'   |( OO'  .-.  ',`'--..._) |  .---'|  |.-') /    _ |   '  .--./ ( OO'  .-.  '(__...--'' |  .---'
 |         |/   |  | |  ||  |  \  ' |  |    |  | OO )\  :` `.   |  |('-. /   |  | |  | |  /  | | |  |
 |  |'.'|  |\_) |  |\|  ||  |   ' |(|  '--. |  |`-' | '..`''.) /_) |OO  )\_) |  |\|  | |  |_.' |(|  '--.
 |  |   |  |  \ |  | |  ||  |   / : |  .--'(|  '---.'.-._)   \ ||  |`-'|   \ |  | |  | |  .___.' |  .--'
 |  |   |  |   `'  '-'  '|  '--'  / |  `---.|      | \       /(_'  '--'\    `'  '-'  ' |  |      |  `---.
 `--'   `--'     `-----' `-------'  `------'`------'  `-----'    `-----'      `-----'  `--'      `------'

Downloading Model from https://www.modelscope.cn to directory: D:\Program Files\CreatorBox\creatorbox\extensions\index_tts\checkpoints

Successfully Downloaded from model IndexTeam/IndexTTS-2.

extensions/index_tts/.venv/scripts/python.exe webui.py --host 0.0.0.0 --port 8014
2025-12-22 17:31:43.013 | INFO  2728  cbinstaller.py:388 - ✅ index_tts started（PID: 11624）
>> Be patient, it may take a while to run in CPU mode.
2025-12-22 17:31:54.693 | WARNING 2728  cbinstaller.py:141 - ⚠️  index_tts already running (PID: 11624 python.exe)
...
>> bpe model loaded from: ./checkpoints\bpe.model
* Running on local URL:  http://0.0.0.0:8014
* To create a public link, set `share=True` in `launch()`.

Configuration Parameters

webapp/extensions/index_tts/data/config.json

{
    "lang": "zh_CN",
    "emo_control_weight": 1,
    "emo_vector": 0.8,
    "emo_text": "",
    "emo_random": false,
    "max_text_tokens_per_segment": 120,
    "do_sample": true,
    "top_p": 0.8,
    "top_k": 30,
    "temperature": 0.8,
    "length_penalty": 0,
    "num_beams": 3,
    "repetition_penalty": 10,
    "max_mel_tokens": 1500
}

注意

• After a successful startup, lang must remain consistent with the page language and only supports zh_CN or en_US.

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

  • Local access: http://127.0.0.1:8014
  • Remote access: https://xxx.gradio.live、https://xxx.ngrok-free.app、https://xxx.loca.lt
  • Your own public IP or domain