Source
Whisper official documentation
Read the primary source.
Reference illustration, not a screenshot of this source.
Whisper
Speech-recognition model · Voice
Open speech-recognition model for transcription, translation and language identification.
Use it for
Use as a general multilingual transcription engine or baseline.
Choose something else for
Speaker identification requires a separate diarisation layer.
Give it
Audio file
Get back
Transcript; Timed segments
How it is operated
Local runtime or a hosted service running Whisper
Availability
Provider capabilities and historical Studio notes are distinguished below. Current account access, credits and runtime readiness were not tested.
How charging works
Local compute, or hosted-service charges.
Where processing happens
Local when run locally; cloud when used through a hosted endpoint.
Language support
Multilingual; accuracy varies by language and model.
Transcribe a recording
★★★★☆ 4/5 for this task
A clear, reusable transcription baseline. Language and hardware affect results; no universal accuracy ranking is implied.
Decision: Use as a general multilingual transcription engine or baseline.
Limits and things to check
- Check names and technical terms; distinguish the open model from hosted transcription products.
Speaker identification requires a separate diarisation layer. Check names and technical terms; distinguish the open model from hosted transcription products.
Evidence
Official capability documentation; no listening benchmark
Catalogue review: 2026-09-05. The evidence note identifies what was verified. This date does not imply a fresh tool test or verification of every linked source.
