Memos unofficial
POST/api/v1/ai:transcribe

Transcribe an audio file

Transcribes an audio file using the instance's configured AI provider. Supply the required audio object with the audio input. The response contains the transcribed text.

  • IdempotentThe SDK sends Idempotency-Key, so a retried request is only applied once.

1 body field

Audio input for transcription.

audioobjectrequired
Required. Audio input.

2 status codes
200Returns the transcribed text.
textstringoptional
The transcribed text.
defaultReturned when the request fails; includes an error code, a developer-facing message, and optional structured details.
codeintegeroptional
The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code].
messagestringoptional
A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client.
detailsarray<object>optional
A list of messages that carry the error details. There is a common set of message types for APIs to use.

Error handling

audio is required and must contain the audio input to transcribe. The audio object's nested fields are not specified here.