ActionDeepgramUpdated June 2026

How do I transcribe audio with Deepgram?

Short answer: You can transcribe audio url in Deepgram by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Deepgram Transcribe Audio URL action to a workflow, map its 5 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Use this action All 2 Deepgram actions

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
Audio URL url	string	Required	Audio URL (required)
Model model	options	Optional	Model. Options: Nova 3 (best), Nova 2, Whisper Large
Language language	string	Optional	Language
Diarize diarize	options	Optional	Diarize. Options: No, Yes
Smart Format smart_format	options	Optional	Smart Format. Options: Yes, No

Sample request

{
  "url": "e.g. https://example.com/path",
  "model": "{{trigger.model}}",
  "language": "{{trigger.language}}",
  "diarize": "{{trigger.diarize}}",
  "smart_format": "{{trigger.smart_format}}"
}

Returns

{
  "results": {
    "channels": [
      {
        "alternatives": [
          {
            "confidence": 0.99,
            "transcript": "Hello world"
          }
        ]
      }
    ]
  },
  "metadata": {
    "duration": 5.2
  }
}

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

FAQ

Questions about Transcribe Audio URL.

What does the Transcribe Audio URL action do in Deepgram?

Submits an audio URL for transcription with Nova-3 (or other Deepgram models) plus options for diarization, language detection, smart formatting. Among the fastest transcription engines available — 5-10× real-time speed on Nova-3.

What inputs does Transcribe Audio URL require?

Required: Audio URL. 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 Deepgram 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 Transcribe Audio URL support batch operations?

Yes. Run Transcribe Audio URL inside a Loop node to process arrays. TinyCommand handles Deepgram's rate limits automatically so you don't have to throttle manually.

More actions

Other Deepgram actions.

Action

Deepgram Aura TTS

Generates speech from text using Deepgram's Aura TTS — optimised for low latency, especially in real-time voice-agent pairing with Deepgram's STT for a unified speech-in/speech-out loop.