LeMUR Task on Transcript: AssemblyAI action

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Transcript IDs transcript_ids	array	Required	Array of completed transcript ids
Prompt prompt	string	Required	Summarize the call in 3 bullets and list action items
Model final_model	options	Optional	Model. Options: Claude Sonnet 4.5 (best), Claude Haiku 3.5, GPT-4o
Max Output Size max_output_size	string	Optional	Max Output Size

Sample request

{
  "transcript_ids": "{{trigger.transcript_ids}}",
  "prompt": "Summarize the call in 3 bullets and list action items",
  "final_model": "{{trigger.final_model}}",
  "max_output_size": "{{trigger.max_output_size}}"
}

Returns

{
  "usage": {
    "input_tokens": 1000,
    "output_tokens": 200
  },
  "response": "Summary: ...",
  "request_id": "req_abc"
}

Use these fields in downstream nodes for routing, logging, or error handling.

FAQ

Questions about LeMUR Task on Transcript.

What does the LeMUR Task on Transcript action do in AssemblyAI?

Runs an LLM task (summarise, Q&A, extract structured data) against one or more completed transcripts. Saves the chain of "fetch transcript → LLM call" by bundling both server-side. Useful for "summarise this call, extract action items as JSON" post-call workflows.

What inputs does LeMUR Task on Transcript require?

Required: Transcript IDs, Prompt. Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if AssemblyAI returns an error?

The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.

Does LeMUR Task on Transcript support batch operations?

Yes. Run LeMUR Task on Transcript inside a Loop node to process arrays. Tiny Command handles AssemblyAI's rate limits automatically so you don't have to throttle manually.

More actions

Other AssemblyAI actions.

Action

Get Transcript

Returns the transcript by ID with the full text, word-level timestamps, speaker labels (if diarization was on), sentiment per utterance (if enabled), and the AI-generated summary. Poll until status=completed or pair with the transcript-ready webhook.

Action

Transcribe Audio

Submits an audio URL for transcription with options for speaker diarization, language detection, sentiment analysis, PII redaction, custom vocabulary. Returns the transcript ID; processing takes ~25% of audio duration on the Best tier.

How do I run an LLM task on an AssemblyAI transcript?

The fields this action accepts.

Apps that pair well as the trigger for LeMUR Task on Transcript.

Questions about LeMUR Task on Transcript.

Other AssemblyAI actions.

Send lemur task on transcript from your workflows.