| $/min | $0.006000 | $0.002500 | $0.003300 | $0.004000 |
|---|---|---|---|---|
| $/min batch | — | — | — | — |
| Streaming | — | ✓ | — | ✓ |
| Realtime | — | ✓ | — | ✓ |
| Languages | 100+ | en | en | 55+ |
| Diarization | included | extra-cost | included | included |
| TTFW | — | — | — | — |
| Verified | 2026-05-19stale 42d | 2026-05-05stale 56d | 2026-05-19stale 42d | 2026-05-19stale 42d |
| Source | provider page ↗ | provider page ↗ | provider page ↗ | provider page ↗ |
| $/1M chars | $30.00 | $25.00 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | — | ✓ included |
| Voice count | — | 217 |
| Languages | en, es, de, fr, nl, it, ja | en, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or |
| SSML support | — | — |
| TTFB | — | 200ms |
| Output formats | wav, mp3, linear16, mulaw, alaw, opus | pcm, wav, mp3, mulaw |
| Verified | 2026-05-19stale 42d | 2026-05-19stale 42d |
| Source | provider page ↗ | provider page ↗ |