Feature-Additionenhancementhelp wanted
Repository metrics
- Stars
- (1,405 stars)
- PR merge metrics
- (Avg merge 2d 4h) (66 merged PRs in 30d)
Description
This issue is to track implementation of Text-to-Speech related features.
- Implement baseline pipeline for TTS using commercial APIs
- Implement + Verify offline TTS via 'local' APIs
- Implement 'stop talking' button to stop playback of pre-recorded audio
- #540
- Implement options for further customization
- #563
- #500
- xtts2
- Kokoro #491
- OuteTTS
- LLaSA
- Sesame (https://www.sesame.com/)
- Spark-TTS https://huggingface.co/SparkAudio/Spark-TTS-0.5B
- Zonos https://huggingface.co/Zyphra/Zonos-v0.1-transformer