Translate Telegram Audio Messages with AI

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": "IvgAFAUOSI3biT4L",
  "name": "Translate Telegram audio messages with AI (55 supported languages) v1",
  "tags": [],
  "nodes": [
    {
      "id": "f91fa0cf-ea01-4fc0-9ef2-754da399b7fb",
      "name": "Telegram Trigger",
      "type": "n8n-nodes-base.telegramTrigger",
      "position": [
        440,
        220
      ],
      "parameters": {
        "updates": [
          "*"
        ],
        "additionalFields": {}
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "057ae05f-2c7d-48c5-a057-a6917a88971c",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1240,
        0
      ],
      "parameters": {
        "width": 556.5162909529794,
        "height": 586.6978417266175,
        "content": "## Translation\n\n- Converts from speech to text.\n\n- Translates the language from the native language to translated language (as specified in settings node)\n\n"
      },
      "typeVersion": 1
    },
    {
      "id": "c6947668-118e-4e23-bc55-1cdbce554a20",
      "name": "Text reply",
      "type": "n8n-nodes-base.telegram",
      "position": [
        2240,
        220
      ],
      "parameters": {
        "text": "={{ $json.text }}",
        "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
        "additionalFields": {
          "parse_mode": "Markdown"
        }
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "93551aea-0213-420d-bf82-7669ab291dae",
      "name": "Telegram1",
      "type": "n8n-nodes-base.telegram",
      "position": [
        1060,
        220
      ],
      "parameters": {
        "fileId": "={{ $('Telegram Trigger').item.json.message.voice.file_id }}",
        "resource": "file"
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "972177e4-b0a4-424f-9ca6-6555ff3271d7",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1520,
        400
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "0e8f610f-03a7-4943-bd19-b3fb10c89519",
      "name": "Input Error Handling",
      "type": "n8n-nodes-base.set",
      "position": [
        860,
        220
      ],
      "parameters": {
        "fields": {
          "values": [
            {
              "name": "message.text",
              "stringValue": "={{ $json?.message?.text || \"\" }}"
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.2
    },
    {
      "id": "c8ab9e01-c9b5-4647-8008-9157ed97c4c3",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        1920,
        0
      ],
      "parameters": {
        "width": 585.8688089385912,
        "height": 583.7625899280566,
        "content": "## Telegram output\n\n- Provide the output in both text as well as speech. \n\n- Many languages are supported including English,French, German, Spanish, Chinese, Japanese.\n\nFull list here:\nhttps://platform.openai.com/docs/guides/speech-to-text/supported-languages\n"
      },
      "typeVersion": 1
    },
    {
      "id": "0898dc4d-c3ad-43df-871f-1896f673f631",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -140,
        0
      ],
      "parameters": {
        "color": 4,
        "width": 489.00549958607303,
        "height": 573.4892086330929,
        "content": "## Multi-lingual AI Powered Universal Translator with Speech \u2b50\n\n### Key capabilities\nThis flow enables a Telegram bot that can \n- accept speech in one of 55 languages \n- translates to another language and returns result in speech\n\n### Use case:\n- Learning a new language\n- Communicate with others while traveling to another country\n\n### Setup\n- Open the Settings node and specify the languages you would like to work with"
      },
      "typeVersion": 1
    },
    {
      "id": "ae0595d2-7e40-4c1e-a643-4b232220d19a",
      "name": "Settings",
      "type": "n8n-nodes-base.set",
      "position": [
        660,
        220
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "501ac5cc-73e8-4e9c-bf91-df312aa9ff88",
              "name": "language_native",
              "type": "string",
              "value": "english"
            },
            {
              "id": "efb9a7b2-5baa-44cc-b94d-c8030f17e890",
              "name": "language_translate",
              "type": "string",
              "value": "french"
            }
          ]
        }
      },
      "typeVersion": 3.3
    },
    {
      "id": "2d3654cf-a182-4916-a50c-a501828c2f6e",
      "name": "Auto-detect and translate",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        1500,
        220
      ],
      "parameters": {
        "text": "=Detect the language of the text that follows.  \n- If it is  {{ $('Settings').item.json.language_native }} translate to {{ $('Settings').item.json.language_translate }}.  \n- If it is in  {{ $('Settings').item.json.language_translate }} translate to {{ $('Settings').item.json.language_native }} .  \n- In the output just provide the translation and do not explain it.  Just provide the translation without anything else.\n\nText:\n {{ $json.text }}\n",
        "promptType": "define"
      },
      "typeVersion": 1.4
    },
    {
      "id": "a6e63516-4967-4e81-ba5b-58ad0ab21ee3",
      "name": "Audio reply",
      "type": "n8n-nodes-base.telegram",
      "position": [
        2240,
        400
      ],
      "parameters": {
        "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
        "operation": "sendAudio",
        "binaryData": true,
        "additionalFields": {}
      },
      "credentials": {
        "telegramApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.1
    },
    {
      "id": "e4782117-03de-41d2-9208-390edc87fc08",
      "name": "OpenAI2",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        1300,
        220
      ],
      "parameters": {
        "options": {},
        "resource": "audio",
        "operation": "transcribe"
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    },
    {
      "id": "b29355f5-122c-4557-8215-28fdb523d221",
      "name": "OpenAI",
      "type": "@n8n/n8n-nodes-langchain.openAi",
      "position": [
        2020,
        400
      ],
      "parameters": {
        "input": "={{ $json.text }}",
        "options": {},
        "resource": "audio"
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.3
    }
  ],
  "active": true,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "ac9c6f40-10c8-4b60-9215-8d4e253bf318",
  "connections": {
    "OpenAI": {
      "main": [
        [
          {
            "node": "Audio reply",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI2": {
      "main": [
        [
          {
            "node": "Auto-detect and translate",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Settings": {
      "main": [
        [
          {
            "node": "Input Error Handling",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Telegram1": {
      "main": [
        [
          {
            "node": "OpenAI2",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Telegram Trigger": {
      "main": [
        [
          {
            "node": "Settings",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Auto-detect and translate",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Input Error Handling": {
      "main": [
        [
          {
            "node": "Telegram1",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Auto-detect and translate": {
      "main": [
        [
          {
            "node": "Text reply",
            "type": "main",
            "index": 0
          },
          {
            "node": "OpenAI",
            "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
• telegramApi

About this workflow

This workflow enables a Telegram bot that can: Accept speech input in one of 55 supported languages Automatically detect the language spoken and translate the speech to another language Responds back with the translated speech output.

Source: https://n8n.io/workflows/2206/ — 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.