Turn audio into text with word-level timestamps.
Transcribes audio into text with word timestamps, speaker labels, and language identification using Azure AI Speech.
When to use it
Use for audio or video transcription, subtitle generation, or spoken-content processing in OpenMontage.
Give it an audio file; it produces a timestamped transcript in the project's artifacts directory.
What you provide
Requires an Azure Speech resource; setup directs the user to create one and obtain its key and region.
The documented pipeline uses OpenMontage's azure_stt tool.
The Fast Transcription integration requires requests rather than the native Speech SDK.
This skill
Azure AI Speech
Uploads audio to Azure