alpha

Create transcriptions

Transcribe a short spoken recording to text, for example to use as a question in alpha_conversations_send: audio is the recording's bytes as base64, at most 3 MiB (3,145,728 bytes) once decoded, in audio/webm, audio/mp4 or audio/wav. Nothing is stored and each call transcribes again; calls are rate limited per credential.

post/api/v1/alpha/transcriptions/create

Request

  • Base URL: https://point11.ai
  • URL: https://point11.ai/api/v1/alpha/transcriptions/create
  • Auth: one of:
    • HTTP bearer
    • OAuth 2 (authorization code, authorization URL https://auth.point11.ai/oauth2/authorize, token URL https://auth.point11.ai/oauth2/token)

Headers

Point11-Organizationstring uuid

Organization to act in. Required for OAuth bearers; an API key acts in the organization that owns it.

Idempotency-Keystring uuid required

UUID naming this intent. Retry with the same key; reuse for other input is 409.

Request body

audiostring base64 required

The recording's bytes, base64-encoded: at most 3145728 bytes once decoded

mediaTypestring required

The recording's media type: audio/webm, audio/mp4, audio/wav (a codecs parameter is accepted)

Response

Success.

textstring required

The transcript; empty when no speech was recognized

Changes

No recorded changes to this operation across all 1 revision of this API.