Typecast MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Typecast MCP or direct API to generate expressive speech, discover voices, manage custom voices, and create production-ready voiceovers through natural language.

Typecast logoTypecast
Api Key

Typecast is an AI voice platform for generating expressive speech and discovering voices. Use it to create natural voiceovers and manage custom voices at scale.

7 Tools

Try Typecast now

Type what you want done — sign in and watch it run live in the Tool Router playground.

TOOL ROUTER PLAYGROUND
Typecast
Try asking
TOOLS

Supported Tools

Every Typecast action and event your agent gets out of the box.

Compose Speech

Generate one audio file from an ordered sequence of speech and pause segments.

Generate Speech

Generate a complete WAV or MP3 audio file from text using a Typecast voice.

Generate Speech With Timestamps

Generate speech plus word, character, or both alignment timestamp arrays.

Get Subscription

Get the connected Typecast API plan, credit usage, concurrency limit, and custom-voice allowance.

Get Voice

Get one voice's metadata, supported models, and available emotions by voice ID.

List Voices

List available built-in and owned custom Typecast voices, optionally filtered by speech model, gender, age, use case, and voice type.

Recommend Voices

Find and rank Typecast voices that match a natural-language description.

SETUP GUIDE

Connect Typecast MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
Install the Composio SDK and your agent framework
2

Create a session with MCP enabled

typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["typecast"],
  mcp: true,
});
Create a session scoped to Typecast and read its MCP URL and headers
3

Connect your agent to the MCP server

typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Generate an expressive voiceover for this product launch intro using a warm narrator voice: Welcome to FlowKit, the fastest way to turn team ideas into shipped work.",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
Pass the session's MCP URL and headers to your agent and run a Typecast request
SETUP GUIDE

Connect Typecast API Tool with your Agent

1

Install Composio

typescript
npm install @composio/core @composio/openai openai
Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
2

Create a Composio session

typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["typecast"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Typecast
3

Run Typecast tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Generate an expressive voiceover for this product launch intro using a warm narrator voice: Welcome to FlowKit, the fastest way to turn team ideas into shipped work." }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
Send a request, execute the Typecast tool calls through the session, and print the final answer

Why Use Composio?

AI Native Typecast Integration

  • Supports both Typecast MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable speech generation and voice lookup
  • Rich coverage for generating audio, discovering voices, and managing custom Typecast voices

Secure Typecast API Key Auth

  • Connect Typecast with your own API key and avoid hard-coding secrets in agent code
  • Use auth_configs.create() and connected_accounts.link() to set up scoped Typecast access per user
  • Composio handles secure credential storage and API request handling for your agents

Agent Optimized Design

  • Tools are tuned for real agent workflows like voiceover creation, voice selection, and custom voice management
  • Clear tool schemas help models pick the right Typecast action without guesswork
  • Comprehensive execution logs so you always know what audio task ran, when, and on whose behalf

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Typecast
  • Scoped, least privilege access to Typecast speech generation and voice resources
  • Full audit trail of agent actions to support review and compliance
FAQ

Frequently asked questions

Yes, Typecast requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

Yes! Composio's Tool Router enables agents to use multiple toolkits. Learn more.

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. Learn more.

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

Start with Typecast.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Typecast tool your agent needs.Free to start.

Start building