StyleTTS 2
StyleTTS 2 is StyleTTS's text to speech model. A TTS model that achieves human-level naturalness by modeling speech styles as latent diffusion processes for expressive synthesis.
StyleTTS's text to speech model. A TTS model that achieves human-level naturalness by modeling speech styles as latent diffusion processes for expressive synthesis.styletts-tts-2 |
| Text to Speech |
| Active |
| StyleTTS |
| Text |
| Audio |
896#248 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
·
·
✓
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| StyleTTS 2 | — | — | — | — | Current |
| Step TTS 2 | — | — | — | — | Available |
| Inworld TTS 1.5 Max | — | — | — | — | Available |
| Inworld TTS 1.5 Mini | — | — | — | — | Available |
| Inworld TTS 1 Max | — | — | — | — | Available |
| TTS-1 | — | — | $0.000 | $0.000 | Available |
| TTS-1 HD | — | — | $0.000 | $0.000 | Available |
| Inworld TTS 1 | — | — | — | — | Available |
| LMNT | — | — | — | — | Available |
| Microsoft TTS | — | — | — | — | Available |
| Microsoft TTS HD | — | — | — | — | Available |