Update Voice Builder links
Browse files
README.md
CHANGED
|
@@ -85,6 +85,10 @@ print(f"Generated {duration:.2f}s of audio")
|
|
| 85 |
- **Higher speaker similarity**: improved similarity across the shared-language set compared with Supertonic 2.
|
| 86 |
- **Expression tags**: supports simple tags such as `<laugh>`, `<breath>`, and `<sigh>`.
|
| 87 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
## Performance Highlights
|
| 89 |
|
| 90 |
Supertonic 3 is designed for practical on-device inference: compact enough to run locally, while staying competitive with much larger open TTS systems.
|
|
|
|
| 85 |
- **Higher speaker similarity**: improved similarity across the shared-language set compared with Supertonic 2.
|
| 86 |
- **Expression tags**: supports simple tags such as `<laugh>`, `<breath>`, and `<sigh>`.
|
| 87 |
|
| 88 |
+
## Custom Voices and Audio Samples
|
| 89 |
+
|
| 90 |
+
The open-weight package includes fixed preset voice styles for immediate local inference. If you want to hear how Supertonic 3 performs with zero-shot custom voice styles, visit the [Audio Sample Demo](https://supertonic3.github.io/) to compare reference audio and generated speech across several use cases. To create your own Supertonic 3 voice-style JSON from reference audio, use [Supertonic Voice Builder](https://supertonic.supertone.ai/voice-builder); purchased Voice Builder styles include downloadable embeddings for both Supertonic 2 and Supertonic 3.
|
| 91 |
+
|
| 92 |
## Performance Highlights
|
| 93 |
|
| 94 |
Supertonic 3 is designed for practical on-device inference: compact enough to run locally, while staying competitive with much larger open TTS systems.
|