index-tts vs GPT-SoVITS
Two Editing & audio projects side by side: what each one is for, what it runs on, and how active it is right now.
index-tts
index-ttsRVC-Boss
GPT-SoVITSIn one line
Voice cloner that reads your script in five languages
Clones a voice from a 5-second clip and reads your text in it
Best for
Short-drama and comic-drama dubbers who need cloned voices in five languages.
Dubbing teams building character voices from short reference clips.
GitHub stars
24k GitHub stars
62k GitHub stars
Stars, last 30 days
+8
+16
Last push
3 days ago
1 month ago
Latest release
v2.5.0, Aug 13, 2026
20250606v2pro, Jun 6, 2025
Forks
2.9k forks
6.7k forks
License
Custom licenseCustom license: read the LICENSE file in the repo before you reuse anything.
MITMIT: you can use and change this code, even in paid products. Just keep the license file.
Models
- IndexTTS-2.5
- IndexTTS-2
- IndexTTS-1.5
- IndexTTS-1.0
- Qwen
- GPT-SoVITS v2Pro / v2ProPlus
- GPT-SoVITS v4
- GPT-SoVITS v3
- GPT-SoVITS v2
- GPT-SoVITS v1
- Fun-ASR-Nano
- SenseVoice
- FunASR
- Faster Whisper Large V3
- UVR5
Languages
English README; UI in Chinese, English, Japanese, Spanish, Arabic
English README; UI in English, Chinese, Japanese, Korean, Turkish
Features
- Clones a voice from one reference clip, with no training per speaker
- Sets emotion with a sad or happy reference clip, an 8-value vector, or text
- emo_alpha (0.0-1.0) controls how strongly the emotion reference pulls the voice
- Changes speaking speed with duration_factor, from 0.5x to 2.0x
- Fixes pronunciation with Pinyin, CMU phonemes or Japanese Kana
- Runs as a Gradio WebUI, a Python API, or a vLLM server
- Clones a voice from a 5-second sample, no training needed
- Trains on about 1 minute of audio for a closer voice match
- Speaks English, Japanese, Korean, Cantonese and Chinese
- Splits vocals from music, slices audio and writes transcripts
- Picks from Fun-ASR-Nano, SenseVoice or classic FunASR for transcription
- Runs in a WebUI or through API scripts
Setup
6 steps
6 steps
Which one to pick
Pick index-tts if…
Short-drama and comic-drama dubbers who need cloned voices in five languages.
Pick GPT-SoVITS if…
Dubbing teams building character voices from short reference clips.
Stars and activity come from GitHub and update daily. We last checked the descriptions on Oct 1, 2026.