This skill is available as a machine-readable YAML playbook via the Framelane MCP server.
Load it into any MCP-capable agent to get the complete workflow without writing integration code.
What this skill does
Submits aPOST /v1/tasks/transcribe job via AssemblyAI, polls until complete, fetches the transcript JSON, and returns it. Word-level timestamps are always included so the output is ready to feed into word_animation in a render request.
Load via MCP
Inputs
| Name | Required | Description |
|---|---|---|
source_url | required | URL of the audio or video file |
source_language | optional | BCP-47 language code (e.g. en). Auto-detected if omitted. |
speaker_labels | optional | Enable speaker diarisation. Default: false. |
Output
Returnstranscript — the full AssemblyAI JSON including text, words[] (with text, start, end per word), and optionally utterances[] when speaker labels are enabled.