GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- GPT-SoVITS enables high‑quality text‑to‑speech synthesis from just one minute of voice data.
- It supports few‑shot voice cloning, allowing personalized voice models with minimal recordings.
- The tool can be integrated into applications that require rapid, user‑specific TTS without large datasets.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Price: Free — Open source
- Category: Audio
- This week: +70 GitHub stars this week
- Source on GitHub (62,317 stars)
- First seen by Liz:
Visit GPT-SoVITS
More in Audio
- VoiceStudio — VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning,…
- ElevenLabs — Lifelike text-to-speech and voice cloning.
- VoxCPM — VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design,…
- sherpa-onnx — Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source…
- index-tts — An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
- edge-tts — Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft…
- pyvideotrans — Translate the video from one language to another and embed dubbing & subtitles.
- OpenVoice — Instant voice cloning by MIT and MyShell. Audio foundation model.
Opening Liz…
