Transcribe audio

OpenAI speech to text

Hosted audio transcription API that turns uploaded recordings or live audio into text, with older models for speaker labels and timestamps.

Your data

Data location: Regional storage and processing in the US, Europe and other regions for /v1/audio/transcriptions8
Retention: No abuse monitoring retention and no application state for /v1/audio/transcriptions8
Used for training: No, unless you opt in8
Zero data retention: Eligible for /v1/audio/transcriptions8

Compliance

Certifications: Not published
HIPAA: Not published

Read from OpenAI’s own pages on 2026-11-04. Every number links to the page a value came from. For agents, the same facts as markdown: /tools/transcribe-audio/openai-transcription.md