StyleTTS2 Models by Columbia University
1 model2024
Last refreshed 2026-10-19. Next refresh: weekly.
Details
ResearcherColumbia University
LicenseMITOSI-approved
Commercial usePermitted
Models1
Released2024
Links
WebsiteAbout
Open-source StyleTTS2 text-to-speech model family with style and prosody control.
Decision facts
- Best fit
- audiotext to speech
- Capability starting point
- StyleTTS2
- Lowest tracked input
- Not tracked
- Closest related family
- AssemblyAI
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| StyleTTS2 | Use when the workload needs text to speech and audio. | 2024-01 | text to speechaudio | Current |
Release Timeline
1 release group2024-01
1 current
StyleTTS2
Currenttext to speechaudio
Specifications(1 models)
| Model | Released |
|---|---|
| StyleTTS2 | 2024-01 |