Convert Text to Speech with OpenAI

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "id": "6Yzmlp5xF6oHo1VW",
  "name": "Text to Speech (OpenAI)",
  "tags": [],
  "nodes": [
    {
      "id": "938fedbd-e34c-40af-af2f-b9c669e1a6e9",
      "name": "When clicking \"Test workflow\"",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        380,
        380
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "1d59db5d-8fe6-4292-a221-a0d0194c6e0c",
      "name": "Set input text and TTS voice",
      "type": "n8n-nodes-base.set",
      "position": [
        760,
        380
      ],
      "parameters": {
        "mode": "raw",
        "options": {},
        "jsonOutput": "{\n  \"input_text\": \"The quick brown fox jumped over the lazy dog.\",\n  \"voice\": \"alloy\"\n}\n"
      },
      "typeVersion": 3.2
    },
    {
      "id": "9d54de1d-59b7-4c1f-9e88-13572da5292c",
      "name": "Send HTTP Request to OpenAI's TTS Endpoint",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        1120,
        380
      ],
      "parameters": {
        "url": "https://api.openai.com/v1/audio/speech",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "sendHeaders": true,
        "authentication": "predefinedCredentialType",
        "bodyParameters": {
          "parameters": [
            {
              "name": "model",
              "value": "tts-1"
            },
            {
              "name": "input",
              "value": "={{ $json.input_text }}"
            },
            {
              "name": "voice",
              "value": "={{ $json.voice }}"
            }
          ]
        },
        "headerParameters": {
          "parameters": [
            {
              "name": "Authorization",
              "value": "Bearer $OPENAI_API_KEY"
            }
          ]
        },
        "nodeCredentialType": "openAiApi"
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.1
    },
    {
      "id": "1ce72c9c-aa6f-4a18-9d5a-3971686a51ec",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        280,
        256
      ],
      "parameters": {
        "width": 273,
        "height": 339,
        "content": "## Workflow Trigger\nYou can replace this manual trigger with another trigger type as required by your use case."
      },
      "typeVersion": 1
    },
    {
      "id": "eb487535-5f36-465e-aeee-e9ff62373e53",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        660,
        257
      ],
      "parameters": {
        "width": 273,
        "height": 335,
        "content": "## Manually Set OpenAI TTS Configuration\n"
      },
      "typeVersion": 1
    },
    {
      "id": "36b380bd-0703-4b60-83cb-c4ad9265864d",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1020,
        260
      ],
      "parameters": {
        "width": 302,
        "height": 335,
        "content": "## Send Request to OpenAI TTS API\n"
      },
      "typeVersion": 1
    },
    {
      "id": "ff35ff28-62b5-49c8-a657-795aa916b524",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        660,
        620
      ],
      "parameters": {
        "color": 4,
        "width": 273,
        "height": 278,
        "content": "### Configuration Options\n- \"input_text\" is the text you would like to be turned into speech, and can be replaced with a programmatic value for your use case. Bear in mind that the maximum number of tokens per API call is 4,000.\n\n- \"voice\" is the voice used by the TTS model. The default is alloy, other options can be found here: [OpenAI TTS Docs](https://platform.openai.com/docs/guides/text-to-speech)"
      },
      "typeVersion": 1
    },
    {
      "id": "5f7ef80e-b5c8-41df-9411-525fafc2d910",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1020,
        620
      ],
      "parameters": {
        "color": 4,
        "width": 299,
        "height": 278,
        "content": "### Output\nThe output returned by OpenAI's TTS endpoint is a .mp3 audio file (binary).\n\n\n### Credentials\nTo use this workflow, you'll have to configure and provide a valid OpenAI credential.\n"
      },
      "typeVersion": 1
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "19d67805-e208-4f0e-af44-c304e66e8ce8",
  "connections": {
    "Set input text and TTS voice": {
      "main": [
        [
          {
            "node": "Send HTTP Request to OpenAI's TTS Endpoint",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When clicking \"Test workflow\"": {
      "main": [
        [
          {
            "node": "Set input text and TTS voice",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• openAiApi

About this workflow

This workflow sends an HTTP request to OpenAI's Text-to-Speech (TTS) model, returning an .mp3 audio recording of the provided text. This template is meant to be adapted for your individual use case, and requires a valid OpenAI credential. Per OpenAI's Usage Policies, you must…

Source: https://n8n.io/workflows/2092/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.