AI · 13 — Transcribe (voice → text)

The opposite direction: read the mp3 that demo 12 saved and turn it back into text with the ◈-wired local Whisper (:8970). Point the Read node at any audio file you like. Run demo 12 first so the file exists.

What’s inside

5 nodes — every type links to its full reference page.

Step	Node	Type
Run	Manual Trigger	`input.manual`
Read mp3	Read File	`input.read-file`
Transcribe	AI Transcribe	`ai.transcribe`
Whisper STT (local)	AI Model	`ai.model`
Transcript	Console	`utility.console`

Import it

Studio → Import — paste the JSON below (or the URL /docs/templates/ai-13-transcribe-voice-text.json).

Or ask the AI Copilot with the JSON pasted after the phrase:

import this workflow json into a new workflow named "AI · 13 — Transcribe (voice → text)"

Any credentials the nodes need are ${credential.…} references — add them once in Admin → Credentials and the template picks them up. Nothing secret ships in a template.

The workflow document (flowdrome.workflow.v1, 5 node types)

{
  "schemaVersion": "flowdrome.workflow.v1",
  "id": "",
  "name": "AI · 13 — Transcribe (voice → text)",
  "version": "0",
  "status": "draft",
  "nodes": [
    {
      "id": "seed",
      "type": "input.manual",
      "label": "Run",
      "category": "trigger",
      "config": {},
      "position": {
        "x": 0,
        "y": 0
      }
    },
    {
      "id": "read",
      "type": "input.read-file",
      "label": "Read mp3",
      "category": "io",
      "config": {
        "path": "./ai-demo-speech.mp3",
        "contentType": "auto",
        "encoding": "base64"
      },
      "position": {
        "x": 530,
        "y": 0
      }
    },
    {
      "id": "hear",
      "type": "ai.transcribe",
      "label": "Transcribe",
      "category": "ai",
      "config": {
        "baseUrl": "http://localhost:8970/v1",
        "apiKey": "",
        "model": "Systran/faster-whisper-tiny.en",
        "audioField": "data",
        "language": "",
        "outputField": "",
        "timeoutMs": 120000
      },
      "position": {
        "x": 1060,
        "y": 0
      },
      "attachments": {
        "model": "stt"
      }
    },
    {
      "id": "stt",
      "type": "ai.model",
      "label": "Whisper STT (local)",
      "category": "ai",
      "config": {
        "provider": "generic-url",
        "baseUrl": "http://localhost:8970/v1",
        "apiKey": "",
        "model": "Systran/faster-whisper-tiny.en",
        "models": [],
        "temperature": 0.2,
        "maxTokens": 512
      },
      "position": {
        "x": 1060,
        "y": 222
      }
    },
    {
      "id": "out",
      "type": "utility.console",
      "label": "Transcript",
      "category": "utility",
      "config": {
        "message": "Heard: “{{ $json.text }}”"
      },
      "position": {
        "x": 1590,
        "y": 0
      }
    }
  ],
  "edges": [
    {
      "id": "e0",
      "sourceNodeId": "seed",
      "sourcePort": "output",
      "targetNodeId": "read",
      "targetPort": "input"
    },
    {
      "id": "e1",
      "sourceNodeId": "read",
      "sourcePort": "output",
      "targetNodeId": "hear",
      "targetPort": "input"
    },
    {
      "id": "e2",
      "sourceNodeId": "hear",
      "sourcePort": "output",
      "targetNodeId": "out",
      "targetPort": "input"
    }
  ],
  "triggers": [
    {
      "id": "t0",
      "nodeId": "seed"
    }
  ],
  "meta": {
    "snippets": [],
    "source": "template-gallery",
    "description": "The opposite direction: read the mp3 that demo 12 saved and turn it back into text with the ◈-wired local Whisper (:8970). Point the Read node at any audio file you like. Run demo 12 first so the file exists."
  }
}

Generated from the verified demo corpus — this exact document seeds and runs on a fresh Flowdrome. Raw JSON: ai-13-transcribe-voice-text.json.