Using Index-TTS as a Dubbing Channel

What is Index-TTS

Index-TTS is an open-source TTS service from Bilibili that supports Chinese and English voice cloning with excellent audio quality.

Index-TTS open-source: https://github.com/index-tts/index-tts

---

Prerequisites

Requirement	Details
pyVideoTrans version	v3.66 or higher
Hardware	NVIDIA GPU recommended
Operating System	Windows (package), Linux/macOS (source deployment)

---

Windows Package (recommended for beginners)

Download

• Baidu Cloud download: https://pan.baidu.com/s/1dmLdhJgBC7HlfY-hITMVeg?pwd=1234
• HuggingFace download: https://huggingface.co/mortimerme/repocollect/resolve/main/indextts2-0529.7z?download=true

Start

1. Download and extract
2. Double-click 启动webui.bat (Start WebUI)
3. Wait for the model to download automatically
4. After startup, the default address is http://127.0.0.1:7860

---

Source Deployment

Follow the official project documentation: https://github.com/index-tts/index-tts

After deployment, start webui.py. The default address is http://127.0.0.1:7860.

---

Using in pyVideoTrans

Configuration Steps

1. Start the Index-TTS WebUI (ensure your browser can open http://127.0.0.1:7860)
2. Open pyVideoTrans, go to Menu → TTS Settings → F5-TTS/Spark-TTS/index-TTS/Dia-TTS
3. Enter in the "IndexURL" text box: http://127.0.0.1:7860
4. Click "Test" — if no errors, configuration is successful
5. Select "Index-TTS" from the "TTS Channel" dropdown on the main screen

Note: Only the official Index-TTS WebUI is supported.

---

Reference Audio Requirements

Item	Requirement
Format	WAV (recommended)
Duration	3–10 seconds (ideal)
Content	Clear pronunciation, no background noise
Location	f5-tts folder under pyVideoTrans root directory

Reference Audio Format

audio_filename.wav#text corresponding to the audio

Source code verification (_index.py): Index-TTS uses the /gen_single Gradio API endpoint and supports v1 and v2 versions. The v2 version adds emotion control (emo_control_method), with the default option being "Same as the voice reference."

---

Troubleshooting

1. Third-party package doesn't work

If you're using a third-party package, replace its webui.py with the one from the official Index-TTS source code, then launch that webui.py.

2. Error: 配音全部失败 Value: 'Same as the voice reference' is not in the list of choices

Or error: Value: '与音色参考音频相同' is not in the list of choices.

Solution: Open the webui.py file in the Index-TTS project, search for i18n("与音色参考音频相同"), and replace it with Same as the voice reference.

3. Connection failed

Make sure:

• Index-TTS WebUI is running
• The address is correct (default: http://127.0.0.1:7860)
• The browser can open the WebUI interface

4. Model download is slow

First launch requires downloading the model. Be patient. For faster downloads, configure a network proxy.