AI · 12 — Speak (text → voice)

Text becomes speech through the ◈-wired local TTS (Kokoro on :8880), PLAYS right in the Console, and is saved to ./ai-demo-speech.mp3 for demo 13 to transcribe. Change the Inject text and Test again.

What’s inside

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

Step	Node	Type
Script	Inject	`input.inject`
Speak	AI Speak	`ai.speak`
Kokoro TTS (local)	AI Model	`ai.model`
Play it	Play Audio	`output.audio`
Save mp3	Write File	`storage.write-file`
Done	Console	`utility.console`

Import it

Studio → Import — paste the JSON below (or the URL /docs/templates/ai-12-speak-text-voice.json).

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

import this workflow json into a new workflow named "AI · 12 — Speak (text → voice)"

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, 6 node types)

{
  "schemaVersion": "flowdrome.workflow.v1",
  "id": "",
  "name": "AI · 12 — Speak (text → voice)",
  "version": "0",
  "status": "draft",
  "nodes": [
    {
      "id": "seed",
      "type": "input.inject",
      "label": "Script",
      "category": "trigger",
      "config": {
        "contentType": "application/json",
        "payload": {
          "text": "Hello! This voice was generated locally, on this machine, by the Flowdrome speak node."
        }
      },
      "position": {
        "x": 0,
        "y": 0
      }
    },
    {
      "id": "speak",
      "type": "ai.speak",
      "label": "Speak",
      "category": "ai",
      "config": {
        "baseUrl": "http://localhost:8880/v1",
        "apiKey": "",
        "model": "kokoro",
        "voice": "af_heart",
        "textField": "text",
        "format": "mp3",
        "timeoutMs": 120000
      },
      "position": {
        "x": 530,
        "y": 0
      },
      "attachments": {
        "model": "tts"
      }
    },
    {
      "id": "tts",
      "type": "ai.model",
      "label": "Kokoro TTS (local)",
      "category": "ai",
      "config": {
        "provider": "generic-url",
        "baseUrl": "http://localhost:8880/v1",
        "apiKey": "",
        "model": "kokoro",
        "models": [],
        "temperature": 0.2,
        "maxTokens": 512
      },
      "position": {
        "x": 530,
        "y": 222
      }
    },
    {
      "id": "play",
      "type": "output.audio",
      "label": "Play it",
      "category": "output",
      "config": {
        "audioField": "",
        "label": ""
      },
      "position": {
        "x": 1060,
        "y": 0
      }
    },
    {
      "id": "save",
      "type": "storage.write-file",
      "label": "Save mp3",
      "category": "io",
      "config": {
        "path": "./ai-demo-speech.mp3",
        "contentMode": "base64",
        "inputField": "audio",
        "append": false,
        "createDirs": true,
        "encoding": "utf8"
      },
      "position": {
        "x": 1590,
        "y": 0
      }
    },
    {
      "id": "out",
      "type": "utility.console",
      "label": "Done",
      "category": "utility",
      "config": {
        "message": "Saved ./ai-demo-speech.mp3 — Test demo 13 to hear it transcribed back."
      },
      "position": {
        "x": 2120,
        "y": 0
      }
    }
  ],
  "edges": [
    {
      "id": "e0",
      "sourceNodeId": "seed",
      "sourcePort": "output",
      "targetNodeId": "speak",
      "targetPort": "input"
    },
    {
      "id": "e1",
      "sourceNodeId": "speak",
      "sourcePort": "output",
      "targetNodeId": "play",
      "targetPort": "input"
    },
    {
      "id": "e2",
      "sourceNodeId": "play",
      "sourcePort": "output",
      "targetNodeId": "save",
      "targetPort": "input"
    },
    {
      "id": "e3",
      "sourceNodeId": "save",
      "sourcePort": "output",
      "targetNodeId": "out",
      "targetPort": "input"
    }
  ],
  "triggers": [
    {
      "id": "t0",
      "nodeId": "seed"
    }
  ],
  "meta": {
    "snippets": [],
    "source": "template-gallery",
    "description": "Text becomes speech through the ◈-wired local TTS (Kokoro on :8880), PLAYS right in the Console, and is saved to ./ai-demo-speech.mp3 for demo 13 to transcribe. Change the Inject text and Test again."
  }
}

Generated from the verified demo corpus — this exact document seeds and runs on a fresh Flowdrome. Raw JSON: ai-12-speak-text-voice.json.