Palatine Speech This workflow corresponds to n8n.io template #17726 — we link there as the canonical source.
This workflow follows the Telegram → Telegram Trigger recipe pattern — see all workflows that pair these two integrations.
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": "WHO9KFGwh8Km3BhP",
"name": "Transcribe Telegram Voice Messages with Palatine Speech",
"tags": [],
"nodes": [
{
"id": "8844f61f-35a7-4c62-92e2-f8d8f223c8a0",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-480,
-1088
],
"parameters": {
"width": 892,
"height": 791,
"content": "## Transcribe Telegram Voice Messages with Palatine Speech\n\n**Who's it for:** Anyone who would rather send a voice note to their Telegram bot than type.\n\nTranscribes Telegram voice messages to text and replies with the transcript (text messages are echoed back).\n\n### How it works\n1. Telegram Trigger receives a new message\n2. Switch routes voice vs. text\n3. Download the voice file from Telegram\n4. Palatine Speech transcribes the audio\n5. Bot replies with the transcript\n\n### Setup\n1. Install `n8n-nodes-palatine-speech` in **Settings \u2192 Community Nodes**.\n2. Add credentials: Telegram Bot API \u00b7 Palatine Speech API.\n3. Set the folder / chat / database IDs on the trigger and destination nodes.\n4. Activate the workflow.\n\n### Customization\n- Reply with an AI summary instead of the raw transcript\n- Log every transcript to Google Sheets\n- Restrict the bot to specific chat IDs\n\n**Requirements:** Telegram Bot API \u00b7 Palatine Speech API\n\n_Uses the community node **Palatine Speech** (`n8n-nodes-palatine-speech`). Install it from the nodes panel: press **+**, search `Palatine`, open the node and click **Install node**._"
},
"typeVersion": 1
},
{
"id": "545eea56-5596-4381-8235-0380fc42fef7",
"name": "Section 1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-496,
-208
],
"parameters": {
"color": 7,
"width": 712,
"height": 472,
"content": "## 1. Receive the audio\nTrigger and fetch the file that needs transcribing."
},
"typeVersion": 1
},
{
"id": "dcbc5f87-eee8-4fa2-8874-c82311ffab5c",
"name": "Section 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
192,
-208
],
"parameters": {
"color": 7,
"width": 224,
"height": 280,
"content": "## 2. Process with Palatine Speech"
},
"typeVersion": 1
},
{
"id": "11db6b00-c941-4c4a-b54e-5440feef19a6",
"name": "Section 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
416,
-208
],
"parameters": {
"color": 7,
"height": 280,
"content": "## 3. Deliver the result"
},
"typeVersion": 1
},
{
"id": "2e81ae7d-1719-4308-a951-cddfcf1d9da1",
"name": "Telegram Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-416,
0
],
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "74140a35-d67d-46e8-bae6-4c7e6d514fbb",
"name": "Voice or Text?",
"type": "n8n-nodes-base.switch",
"position": [
-192,
0
],
"parameters": {
"rules": {
"values": [
{
"outputKey": "Voice",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "voice-cond",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.voice?.file_id }}",
"rightValue": ""
}
]
},
"renameOutput": true
},
{
"outputKey": "Text",
"conditions": {
"options": {
"version": 2,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "loose"
},
"combinator": "and",
"conditions": [
{
"id": "text-cond",
"operator": {
"type": "string",
"operation": "exists",
"singleValue": true
},
"leftValue": "={{ $json.message.text }}",
"rightValue": ""
}
]
},
"renameOutput": true
}
]
},
"options": {}
},
"typeVersion": 3.2
},
{
"id": "9a9990e9-e7c9-4587-afe8-bd5371350353",
"name": "Download Voice File",
"type": "n8n-nodes-base.telegram",
"position": [
32,
-96
],
"parameters": {
"fileId": "={{ $json.message.voice.file_id }}",
"resource": "file",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "b1589e51-3ce5-4c9b-81b2-45ce812980b4",
"name": "Echo Text Message",
"type": "n8n-nodes-base.telegram",
"position": [
32,
96
],
"parameters": {
"text": "={{ $json.message.text }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "b379e9d1-288f-45bd-bd7b-c9a8007620b3",
"name": "Palatine Speech Transcription",
"type": "n8n-nodes-palatine-speech.palatineSpeech",
"position": [
256,
-96
],
"parameters": {
"model": "palatine_large_highspeed",
"polling": {},
"requestOptions": {}
},
"credentials": {
"palatineSpeechNodeApi": {
"name": "<your credential>"
}
},
"typeVersion": 3
},
{
"id": "d3a31744-c455-4059-93fe-d15f85d7ff40",
"name": "Send Transcription Reply",
"type": "n8n-nodes-base.telegram",
"position": [
480,
-96
],
"parameters": {
"text": "={{ $json.transcription }}",
"chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}",
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
}
],
"active": true,
"settings": {
"binaryMode": "separate",
"executionOrder": "v1"
},
"versionId": "3946a75e-8c24-4881-940c-eb74a04bd8c9",
"nodeGroups": [],
"connections": {
"Voice or Text?": {
"main": [
[
{
"node": "Download Voice File",
"type": "main",
"index": 0
}
],
[
{
"node": "Echo Text Message",
"type": "main",
"index": 0
}
]
]
},
"Telegram Trigger": {
"main": [
[
{
"node": "Voice or Text?",
"type": "main",
"index": 0
}
]
]
},
"Download Voice File": {
"main": [
[
{
"node": "Palatine Speech Transcription",
"type": "main",
"index": 0
}
]
]
},
"Palatine Speech Transcription": {
"main": [
[
{
"node": "Send Transcription Reply",
"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.
palatineSpeechNodeApitelegramApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow listens for new Telegram bot messages, transcribes incoming voice notes using Palatine Speech, and replies with the transcript, while echoing back any text messages unchanged. Triggers when a new message is received by your Telegram bot. Checks whether the incoming…
Source: https://n8n.io/workflows/17726/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
N8N Complete Final. Uses telegramTrigger, dataTable, telegram, mqtt. Event-driven trigger; 58 nodes.
Telegram Trigger, Data Table, Telegram +3
Pede Ai. Uses httpRequest, telegram, postgres, telegramTrigger. Event-driven trigger; 57 nodes.
HTTP Request, Telegram, Postgres +1
TextMain. Uses telegramTrigger, stopAndError, telegram, httpRequest. Event-driven trigger; 56 nodes.
Telegram Trigger, Stop And Error, Telegram +2
Pede Ai. Uses httpRequest, telegram, postgres, telegramTrigger. Event-driven trigger; 53 nodes.
HTTP Request, Telegram, Postgres +1
📄 Documentation: Notion Guide
Telegram Trigger, @Blotato/N8N Nodes Blotato, Telegram +1