Scribe v2 vs Whisper Large V3 Turbo
rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.
| specification | Scribe v2 elevenlabs/scribe-v2 | Whisper Large V3 Turbo openai/whisper-large-v3-turbo |
|---|---|---|
| audio input · usd / minute | $0.00366667 | $0.00066667 |
| modalities · in → out | takes audio in, gives text out | takes text and audio in, gives text out |
| model type | Speech to text | Speech to text |
pricing
| base api rates · usd per minute | Scribe v2 elevenlabs/scribe-v2 | Whisper Large V3 Turbo openai/whisper-large-v3-turbo |
|---|---|---|
| audio input | $0.00366667 | $0.00066667 |
Whisper Large V3 Turbo bills a minimum of 10 seconds of audio per request. a shared cost estimate needs models of one type with token pricing; compare the published rates and billing units here.
specifications
| as published | Scribe v2 elevenlabs/scribe-v2 | Whisper Large V3 Turbo openai/whisper-large-v3-turbo |
|---|---|---|
| creator | elevenlabs | OpenAI |
| model type | Speech to text | Speech to text |
| context window | not published | not published |
| input | takes audio in, gives text out | takes text and audio in, gives text out |
| output | text | text |
| tool calling | not verified | not verified |
| endpoint | /v1/audio/transcriptions | /v1/audio/transcriptions |
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
benchmarks
| primary configuration | Scribe v2 elevenlabs/scribe-v2 no benchmarks yet | Whisper Large V3 Turbo openai/whisper-large-v3-turbo speech-to-text |
|---|---|---|
| intelligence index · gateway rank | not measured | not measured |
Whisper Large V3 Turbo source ↗
each column describes the tested configuration named under the model; performance and costs can differ on impossibl. a score one model was not measured on is left blank rather than scored zero. indices are ranked against every model on the gateway with one. last checked 2026-10-14.
summary
Scribe v2 and Whisper Large V3 Turbo are available through the Impossibl API. they share the /v1/audio/transcriptions endpoint; the model identifier selects the model for a request.
Scribe v2 is created by elevenlabs. Its context window is not published. Base API pricing (USD): $0.00366667 per minute of audio.
Whisper Large V3 Turbo is created by OpenAI. Its context window is not published. Base API pricing (USD): $0.00066667 per minute of audio.
Scribe v2 →Whisper Large V3 Turbo →
this page compares Scribe v2 vs Whisper Large V3 Turbo as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.
view the source catalog ↗comparison as markdown ↗report a correction →