Databricks `ai_transcribe()` SQL Function for Audio Transcription (Beta)
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.
https://docs.databricks.com/aws/en/release-notes/product/2026/august#ai_transcribe-function-beta
Related releases
- Databricks Lakebase Snapshots API (Beta) for Programmatic Management Databricks Release Notes ·
- Databricks Introduces Session Restore for Serverless Jobs in Public Preview Databricks Release Notes ·
- Announcing On-Demand State Repartitioning for Apache Spark Structured Streaming on Databricks Databricks Blog ·
- Databricks Genie now displays visualizations directly in Slack replies Databricks Release Notes ·
- Databricks Introduces Configurable Data Retention for System Tables (Beta) Databricks Release Notes ·
- Databricks Terraform Provider v1.132.0 Adds Domain & Sandbox Management Terraform Databricks Provider Releases ·