databricks Databricks Release Notes ·

Databricks `ai_transcribe()` SQL Function for Audio Transcription (Beta)

aidatabrickspreviewdata-scientist
feature announcement

Databricks has introduced the `ai_transcribe()` SQL function, enabling users to transcribe audio files directly into text within their data workflows. This function returns transcripts as time-stamped segments and can label speakers via diarization if enabled. Outputting a VARIANT value, it facilitates chaining with other AI Functions for advanced processing. This new audio transcription capability is currently available in Beta.

Features (1)
  • New ai_transcribe() SQL function for audio transcription

    The `ai_transcribe()` SQL function transcribes audio files into text, returning time-stamped segments. When speaker diarization is enabled for the workspace, it labels each segment with a speaker. Its VARIANT output allows chaining with other AI Functions for further processing.

Read the original announcement →

https://docs.databricks.com/aws/en/release-notes/product/2026/august#ai_transcribe-function-beta

Related releases