PhononOn-Device Text-To-Speech
Deploy now.
On all your devices.
Listen now
With Voice Cloning
| Model | Weights | Word Error Rate ↓ | Speaker Similarity ↑ |
|---|---|---|---|
| Phonon | ~100M | 1.00% | 59.51% |
| Kani TTS 2 | 450M | 4.97% | 40.73% |
| NeuTTS Air | 552M | 2.18% | 47.51% |
| NeuTTS Nano | 229M | 1.71% | 40.15% |
| PocketTTS | 100M | 1.27% | 49.13% |
Without Voice Cloning
| Model | Weights | Word Error Rate ↓ |
|---|---|---|
| Phonon | ~100M | 0.83% |
| Kokoro | 82M | 0.90% |
| Magpie | 357M | 0.89% |
| Supertonic 2 | 66M | 2.63% |
Join the Beta