GitHub · Python
Fixed-Seed/Robin
Robin, an open-weights speech model: design a voice from text, re-voice your own takes, train a voice LoRA. 48 kHz, English and Japanese, with ComfyUI nodes.
- Stars
- 15
- Forks
- 0
- Stars gained in 24 hours
- +2
- Forks gained in 24 hours
- 0
Topics: comfyui, japanese, lora, speech-synthesis, text-to-speech, tts
Latest data point: Nov 20, 2026 · 15 stars · 0 forks