Model Summary
| Model | Positioning | Languages | Voice Settings | Extra Features |
|---|---|---|---|---|
| Sona Speech 1 | 旧フラッグシップモデル | 3 | Advanced | Phonemes with Timestamp, Streaming |
| Sona Speech 2 | 最新フラッグシップモデル | 23 | Advanced | Phonemes with Timestamp, Normalized Text |
| Sona Speech 2 Flash | 軽量 / 低レイテンシ | 23 | Core | Phonemes with Timestamp, Normalized Text |
| Supertonic API 1 | 超軽量モデル | 5 | Minimal | – |
Supported Languages
| Model | Languages |
|---|---|
| Sona Speech 1 | en, ko, ja |
| Sona Speech 2 | en, ko, ja, bg, cs, da, el, es, et, fi, hu, it, nl, pl, pt, ro, ar, de, fr, hi, id, ru, vi |
| Sona Speech 2 Flash | en, ko, ja, bg, cs, da, el, es, et, fi, hu, it, nl, pl, pt, ro, ar, de, fr, hi, id, ru, vi |
| Supertonic API 1 | en, ko, ja, es, pt |
Supported Voice Settings
| Model | Voice Settings |
|---|---|
| Sona Speech 1 | pitch_shift, pitch_variance, speed, duration, similarity, text_guidance |
| Sona Speech 2 | pitch_shift, pitch_variance, speed, duration, similarity, text_guidance, subharmonic_amplitude_control |
| Sona Speech 2 Flash | pitch_shift, pitch_variance, speed, duration, subharmonic_amplitude_control |
| Supertonic API 1 | speed |
Additional Features
| Model | Supported Features |
|---|---|
| Sona Speech 1 | include_phonemes, streaming |
| Sona Speech 2 | include_phonemes, normalized_text |
| Sona Speech 2 Flash | include_phonemes, normalized_text |
| Supertonic API 1 | – |
Quick Selection Guide
| このような場合 | 推奨モデル |
|---|---|
| 既存システムとの互換性やストリーミング出力が必要 | Sona Speech 1 |
| 総合的に最高の音声品質を求める場合 | Sona Speech 2 |
| 低レイテンシかつ軽量な推論が必要 | Sona Speech 2 Flash |
| 最小限の設定で素早く導入したい場合 | Supertonic API 1 |