Fish Audio MCP for AI Agents

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Fish Audio MCP or direct API to synthesize speech, transcribe recordings, clone voices, and power conversational voice agents through natural language.

Fish Audio logoFish Audio
Api Key

Fish Audio is an AI voice platform for speech synthesis, transcription, voice cloning, and conversational voice APIs. Use it to ship natural, low-latency voice experiences without building audio models from scratch.

10 Tools

Try Fish Audio now

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

TOOL ROUTER PLAYGROUND
Fish Audio
Try asking
TOOLS

Supported Tools

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

Configure Agent

Partially update an agent's draft prompt, voice, and core conversation behavior without publishing it.

Create Agent

Create a private Fish Audio agent, optionally with an initial prompt, voice, and core conversation settings.

Delete Agent

Permanently delete a Fish Audio agent by ID; use only when deletion is explicitly intended.

Get Account Balance

Return the connected Fish Audio account's package allowance and API credit so an agent can distinguish free quota from paid credit.

Get Agent

Return an agent's workspace metadata together with its current draft conversation configuration.

Get Voice Model

Get a Fish Audio voice model by ID and inspect whether it is trained and suitable for synthesis.

List Agents

Search agents in the connected Fish Audio workspace, including draft or archived agents when requested.

List Agent Sessions

List conversation sessions for the workspace or a specific agent, filtered by lifecycle status, caller, or creation time.

List Voice Models

Search public or workspace-owned Fish Audio voice models.

Synthesize Speech

Generate downloadable speech with Fish Audio's free S2.

SETUP GUIDE

Connect Fish Audio MCP Tool with your Agent

1

Install Composio

typescript
npm install @composio/core ai @ai-sdk/openai @ai-sdk/mcp
Install the Composio SDK for Python or TypeScript
2

Initialize Client and Create Tool Router Session

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

const composio = new Composio({ apiKey: 'your-api-key' });
const session = await composio.create('your-user-id');
console.log(`Tool Router session created: ${session.mcp.url}`);
Import and initialize the Composio client, then create a Tool Router session for Fish Audio
3

Connect to AI Agent

typescript
import { openai } from '@ai-sdk/openai';
import { experimental_createMCPClient as createMCPClient } from '@ai-sdk/mcp';
import { generateText } from 'ai';

const client = await createMCPClient({
  transport: {
    type: 'http',
    url: session.mcp.url,
    headers: {
      'x-api-key': 'your-composio-api-key',
    },
  },
});

const tools = await client.tools();
const { text } = await generateText({
  model: openai('gpt-4o'),
  tools,
  messages: [{
    role: 'user',
    content: 'Generate speech audio saying "Welcome to our product demo" using Fish Audio text to speech'
  }],
  maxSteps: 5,
});

console.log(`Agent: ${text}`);
Use the MCP server with your AI agent (Anthropic Claude or Mastra)
SETUP GUIDE

Connect Fish Audio API Tool with your Agent

1

Install Composio

typescript
npm install @composio/openai
Install the Composio SDK
2

Initialize Composio and Create Tool Router Session

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

const composio = new Composio({
  provider: new OpenAIResponsesProvider(),
});
const openai = new OpenAI({});
const session = await composio.create('your-user-id');
Import and initialize Composio client, then create a Tool Router session
3

Execute Fish Audio Tools via Tool Router with Your Agent

typescript
const tools = session.tools;
const response = await openai.responses.create({
  model: 'gpt-4.1',
  tools: tools,
  input: [{
    role: 'user',
    content: 'Generate speech audio saying "Welcome to our product demo" using Fish Audio text to speech'
  }],
});
const result = await composio.provider.handleToolCalls(
  'your-user-id',
  response.output
);
console.log(result);
Get tools from Tool Router session and execute Fish Audio actions with your Agent

Why Use Composio?

AI Native Fish Audio Integration

  • Supports both Fish Audio MCP and direct API based integrations
  • Structured, LLM-friendly schemas for reliable speech synthesis, transcription, and voice cloning
  • Rich coverage for creating audio, processing voice input, and building voice-first agent workflows

Managed Auth

  • Secure Fish Audio API key storage without hard-coding secrets in your agent code
  • Central place to manage, scope, and revoke Fish Audio access across users and environments
  • Use auth_configs.create(), connected_accounts.link(), and mcp.create() to wire credentials into production agent workflows

Agent Optimized Design

  • Tools are tuned for language models, so agents can call Fish Audio actions with clear inputs and fewer mistakes
  • Comprehensive execution logs show which voice, transcription, or audio generation action ran, when, and for whom
  • Works cleanly with chatbots, copilots, and background agents that need voice output or audio understanding

Enterprise Grade Security

  • Fine-grained RBAC so you control which agents and users can access Fish Audio
  • Scoped, least privilege access for voice generation, transcription, and cloning workflows
  • Full audit trail of Fish Audio agent actions to support review, debugging, and compliance
FAQ

Frequently asked questions

Yes, Fish Audio 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 Fish Audio.It takes 30 seconds.

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

Start building