Aratako / Irodori-TTS
A Flow Matching-based Text-to-Speech Model with Emoji-driven Style Control
Why this job: says: text to speech, tts; topics: text-to-speech, tts, voice-cloning, speech-synthesis
What it does
- Flow Matching TTS. Rectified Flow Diffusion Transformer (RF-DiT) over continuous DACVAE latents
- Voice Cloning. Zero-shot voice cloning from reference audio
- Multi-modal Voice Design. v4-Small combines text, reference speech, and caption text for voice identity plus style/emotion control
- Long Reference Audio. One or more reference clips can be concatenated up to the checkpoint's 120-second limit
- Emoji-based Style Control. Emoji annotations in input text can influence delivery and non-verbal vocal expressions in supported checkpoints
Get started
git clone https://github.com/Aratako/Irodori-TTS.git
cd Irodori-TTS
uv sync --extra cu128
# NVIDIA CUDA 12.8 (Linux/Windows) - Maintenance
- Active
- Last commit today
- Stars
- 1,575
- +61 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 57% closed
- 9 still open
- Pull requests
- 13 merged
- 9 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| RVC-Boss / GPT-SoVITS | 64,596 | 9 days ago | MIT | No downloads |
| OpenMOSS / MOSS-TTS | 4,310 | 2 months ago | Apache-2.0 | No downloads |
| herimor / voxtream | 259 | 25 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- diffusion-models
- flow-matching
- python
- speech-synthesis
- text-to-speech
- tts
- voice-cloning
Project record
- JobSpeech and audio
- StatusFeatured
- Commits54
- Forks186
- Watching18
- Stars in 28 days+147
- CreatedFeb 25, 2026
- First seen by usNov 7, 2026
- CheckedNov 9, 2026