TollNode

Chatterbox Turbo API and MCP for AI agents

TollNode gives Claude, Cursor or any AI agent Chatterbox Turbo, Resemble AI's fast, expressive text-to-speech model with 20 voices, over API and MCP, from $0.018 per clip (up to 500 characters), with no subscription.

Send 'Thanks for calling. [chuckle] Your order left the...' and get an audio file link back in seconds.

No subscription · Sign-up optional · From $0.018 per call · Charged only when it works · No Resemble AI account needed

Claude Code

Read this out loud: Thanks for calling. [chuckle] Your order left the warehouse this morning and...

TollNode · Resemble AI · speech-chatterbox-turbo$0.018 · 1 audio file

ResultDetail
File1 audio link, does not expire
VoiceLaura

Real result, shown below.

Works in Claude Code, Cursor, Codex, VS Code and any MCP agent.

Chatterbox Turbo audio examples

Made by this node in our own tests, from the request shown under each.

“Thanks for calling! [chuckle] Your order left the warehouse this morning and should reach you before noon tomorrow.”

AI-generatedvoice: Laura

The request that made it

Send the same body to get this kind of result. Change the prompt or the options to get your own.

request body
{
  "text": "Thanks for calling! [chuckle] Your order left the warehouse this morning and should reach you before noon tomorrow.",
  "voice": "Laura"
}

What you control with Chatterbox Turbo

Failed calls are never charged. Image and audio links returned by TollNode don't expire.

What people ask their AI to do with it

Use it as a Chatterbox Turbo MCP server in Claude, Cursor or Codex

Connect once. Then just ask.

Paste this into Claude Code, Cursor or Codex. It connects TollNode and gives your agent a small wallet. Add a few dollars of USDC and you're done.

terminal
npx agentcash add https://tollnode.com

Copy for your AI agent

Paste this into your agent so it knows what this node does and how to call it.

prompt
You can use TollNode's Chatterbox Turbo node to make a audio file. Call POST https://tollnode.com/api/v1/nodes/speech-chatterbox-turbo with text (required), voice (optional). The price is one flat price per call and is charged only when a result is returned. Over MCP, call the "speech-chatterbox-turbo" tool; use list_models to see prices. Give me the file link when it is done.

Price

$0.034

per 1,000 characters

One call: $0.018 per clip (up to 500 characters)

Charged only when a call returns a result. Failed or empty calls cost $0.

Chatterbox Turbo without a Resemble AI account

FAQ

Is this the official Resemble AI API?
No. TollNode is an independent service. It gives your agent access to Chatterbox Turbo through its own API and MCP server, priced per clip, with no Resemble AI account needed.
Can I use it as a Chatterbox Turbo MCP server in Claude?
Yes. Add https://tollnode.com/mcp in Claude Code, Claude Desktop or Cursor, and the "speech-chatterbox-turbo" tool appears with its options and prices.
How much does a call cost?
One flat price per clip, the same for every call, shown above. There is nothing to choose that changes it.
Which voices can I use?
20 voices, including Aaron, Abigail, Anaya, Andy, Archer. Set voice in the request; the default is used if you leave it out.
What if nothing comes back?
You're not charged. TollNode only collects payment when a usable result is returned.
How long are the links valid?
They don't expire. Download the file or keep the link.
How do I pay for Chatterbox Turbo?
Your agent sends the request, gets an HTTP 402 with the exact price (from $0.018 per call), signs a USDC payment on Base and retries. Or use an account balance with an API key. Either way you are charged only when a result comes back.
What does the Chatterbox Turbo response look like?
A JSON object with a link to the finished file. The link does not expire, so you can download it later or keep the link.

Ready in a minute

Connect your AI
For developers: endpoint, inputs and an example response

POST https://tollnode.com/api/v1/nodes/speech-chatterbox-turbo

Input

FieldTypeNotes
seedinteger
text*stringUp to 500 characters. Tags such as [laugh], [sigh], [chuckle], [gasp] add expression
voiceenumDefault Andy (Aaron, Abigail, Anaya, Andy, Archer, Brian, Chloe, Dylan, Emmanuel, Ethan, Evelyn, Gavin, Gordon, Ivan, Laura, Lucy, Madison, Marisol, Meera, Walter)

Example response

{
  "audio": [
    "https://tollnode.com/api/v1/files/00000000-0000-0000-0000-000000000000/0"
  ]
}

Also described in the OpenAPI file and llms.txt. Setup for every app: Agents & MCP.