Install
In a self-hosted n8n: Settings, Community Nodes, Install, then enter the package name n8n-nodes-readaloud (npm). Then create a 'ReadAloud API' credential with your key and leave Base URL at https://api.readaloudai.org. Create a ReadAloud API key at https://readaloudai.org/developers and export it as READALOUD_API_KEY; new accounts start with free credits.
This is a community node, not an n8n-verified node. Your n8n instance must allow community nodes that n8n has not verified.Quickstart
Quickstart (json)
{
"nodes": [
{
"parameters": {
"path": "readaloud-demo",
"responseMode": "lastNode"
},
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"typeVersion": 2,
"position": [
0,
0
]
},
{
"parameters": {
"resource": "speech",
"operation": "textToSpeech",
"text": "Thanks for calling. How can I help you today?",
"voice": "readaloud-default",
"format": "mp3",
"speed": 1
},
"name": "ReadAloud",
"type": "n8n-nodes-readaloud.readAloud",
"typeVersion": 1,
"position": [
250,
0
],
"credentials": {
"readAloudApi": {
"id": "<select your ReadAloud API credential>",
"name": "ReadAloud API"
}
}
},
{
"parameters": {
"operation": "write",
"fileName": "/path/to/allowed/folder/speech.mp3",
"dataPropertyName": "data",
"options": {}
},
"name": "Write Binary File",
"type": "n8n-nodes-base.readWriteFile",
"typeVersion": 1,
"position": [
500,
0
]
}
],
"connections": {
"Webhook": {
"main": [
[
{
"node": "ReadAloud",
"type": "main",
"index": 0
}
]
]
},
"ReadAloud": {
"main": [
[
{
"node": "Write Binary File",
"type": "main",
"index": 0
}
]
]
}
}
}What was tested
Checked with n8n-nodes-readaloud (npm), in a local n8n 2.42.6 on Node 24.17.0. Version tested: 0.1.2. Date: October 10, 2026. This is one dated check against the live API. Other versions, and later releases, may behave differently.
What worked
- n8n's community-package install route installed n8n-nodes-readaloud 0.1.2 from npm into a local n8n 2.42.6 (the route the Community Nodes screen uses), and n8n reported one installed node, ReadAloud.
- A workflow of Webhook, ReadAloud and Write Binary File, using a ReadAloud API credential, finished with status success. The node output was {voice: readaloud-default, format: mp3, characters: 45, bytes: 39213, sampleRate: 24000}.
- The file written by Write Binary File was 39,213 bytes, started with an ID3 tag, and ffprobe read it as 24 kHz mono MP3 of 2.45 seconds.
- The node is configured entirely through its fields (voice, format, speed, text), so the workflow needed no Code or HTTP Request node.
Limits and what is not supported
- Only the MP3 format and the voice readaloud-default were run. WAV, Opus and PCM, the speed field and the options are untested by us.
- We ran a self-hosted n8n 2.42.6, not n8n Cloud, and did not use the editor: the credential and workflow were created through n8n's internal REST routes. We did not run the credential's Test button, and we did not run the node as an AI-agent tool.
- The node's default for the voice field is a legacy voice id that the API still accepts as an alias; set the field to readaloud-default as in the quickstart.
- ReadAloud Live has one English voice. Each item may hold up to 5,000 characters, so longer text must be split into several items first. Version 0.1.2 is in n8n's review and is not verified by n8n.
Limits that apply to every integration
- 5,000 characters per request. Split longer text and send it in order.
- Output formats on the OpenAI-compatible route: mp3 (default, 24 kHz), opus (48 kHz, Ogg), wav (24 kHz) and pcm (24 kHz, 16-bit, mono); aac and flac return 400.
- No SSML and no audio tags.
- Beyond capacity the API returns 429 (HTTP) or an "at capacity" error with close code 1013 (WebSocket); retry with a short backoff.
What ReadAloud costs
- ReadAloud Live: $4 per 1M characters ($0.004 per 1,000), the low-latency tier, built for live calls and voice agents.
- ReadAloud Studio: $10 per 1M characters ($0.01 per 1,000), the higher-priced tier for read-aloud and narration, with several English voices.
Billing is per character of speech that finishes; cancelled requests are not billed, and there are no minimums. Every account gets a one-time grant of free credits (worth $0.10, about 10,000 characters of speech). It is one capped pool per account, shared across all of the account's keys and across speech, transcription, dubbing, voice conversion and voice design, and it is used first. When it runs out, requests return 402 until a payment method is added, then billing is pay as you go. Current prices are on the Voice API page (/developers).
Common questions
- Is this an official, verified n8n node?
- No. It is a community node published on npm, and version 0.1.2 is in n8n's review. Until that finishes, install it from npm by package name. We make no claim of n8n verification.
- Where does the audio end up?
- In the binary property data of the output item (the name can be changed under Options). Connect a Write Binary File, Google Drive, S3, email or HTTP Request node after it.
- Why did my Write Binary File node say access is not allowed?
- In our run, n8n 2.42.6 refused to write outside its permitted files folder until we pointed the N8N_RESTRICT_FILE_ACCESS_TO setting at it. Write into a folder your instance allows.
- Can an AI agent call it?
- The package declares the node usable as a tool. We did not run it inside an AI agent workflow, so test that path yourself.
Something here does not match what you see? Tell us at support@readaloudai.org.