Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
| 1 model | elevenlabsElevenLabs: Scribe v2Remove × |
|---|---|
| What’s different | ElevenLabs Scribe v2 is a speech-to-text model that transcribes audio in 90+ languages with word-level timestamps, optional speaker diarization, and audio-event tagging. |
| Date | Oct 7, 2026Listed |
API prices USD · provider configuration shown below | |
| Listed rate | $30.5556 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ |
| Provider endpoints | 1 endpoint → |
Specifications | |
| Context window | — |
| Max output | — |
| Parameters | — |
| Audio input | Supported |