Supertonic 3
Free text-to-speech in your browser
Coming soon to MiniSpeech.
soon| Type | text → speech |
| Size | ≈ 399 MB · to be quantized |
| Languages | English, Korean, Japanese, Arabic, Bulgarian, Czech, Danish, German, Greek, Spanish, Estonian, Finnish, French, Hindi, Croatian, Hungarian, Indonesian, Italian, Lithuanian, Latvian, Dutch, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Swedish, Turkish, Ukrainian, Vietnamese |
| License | OpenRAIL-M |
| Runs on | fp32 · graphics card (WebGPU) · 399 MB |
| Credits | Supertonic 3 by Supertone Inc. (OpenRAIL-M weights, MIT SDK). Use restrictions of the OpenRAIL-M license apply. |
| Original project | github.com/supertone-inc/supertonic |
Files (revision 3cadd1ee63)
| File | Size | SHA-256 |
|---|---|---|
| LICENSE | 15 kB | 0d944a9110fed9a9… |
| config.json | 1 kB | 4099082b107a9d40… |
| onnx/duration_predictor.onnx | 3.7 MB | c3eb91414d5ff8a7… |
| onnx/text_encoder.onnx | 36 MB | c7befd5ea8c31197… |
| onnx/vector_estimator.onnx | 257 MB | 883ac868ea0275ef… |
| onnx/vocoder.onnx | 101 MB | 085de76dd8e8d583… |
| onnx/tts.json | 8 kB | 42078d3aef1cd43a… |
| onnx/unicode_indexer.json | 278 kB | 9bf7346e43883a81… |
| + 10 voice (voice_styles/*.json) | ||