Fish Audio MCP server for AI agents and assistants

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/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: ["fish_audio"],
  mcp: true,
});
Create a session scoped to Fish Audio 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 speech audio saying \"Welcome to our product demo\" using Fish Audio text to speech",
  stopWhen: stepCountIs(10),
});

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

Connect Fish Audio 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: ["fish_audio"] });
const tools = await session.tools();
Initialize Composio with the OpenAI Responses provider and create a session scoped to Fish Audio
3

Run Fish Audio tools with your agent

typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Generate speech audio saying \"Welcome to our product demo\" using Fish Audio text to speech" }],
});

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 Fish Audio tool calls through the session, and print the final answer

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.

Yes. Composio is SOC 2 Type II compliant and is built to keep your Fish Audio connection and credentials secure. OAuth tokens and API keys are encrypted, and sensitive customer data is protected at rest and in transit.

Composio also undergoes independent security testing and continuously monitors its systems for security threats. You can review the latest reports and policies in the Composio Trust Center.

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

Create the key in your Fish Audio account settings, then paste it once on Composio's connection page. Composio stores it encrypted and uses it only for the Fish Audio actions your agent runs. Nobody else in your workspace can read it, and you can revoke it inside Fish Audio at any time.

When you connect a Fish Audio account through Composio, every action runs under that account, so anything the agent creates, sends, or changes shows up in Fish Audio as done by you. Keep an approval step in your prompt for actions with side effects, such as sending or deleting, and have the agent draft first.

Whatever the credentials you connect allow inside Fish Audio. If Fish Audio lets you scope a key to specific permissions, create a scoped one so the agent can only do what you intend. You can revoke the key inside Fish Audio at any time.

Yes. Composio supports multiple connected accounts for the same app, and that works in Claude, ChatGPT, or any other assistant you connect through Composio. Give each Fish Audio connection a name such as work or personal, and the assistant uses the one you mention in the request. Each account keeps its own credentials and nothing is merged.

The connection stops working the moment Fish Audio rejects the old key. Create a new key in Fish Audio and reconnect the account from the Composio dashboard or by asking your agent to reconnect Fish Audio. Nothing else changes.

Composio's free Hobby plan includes 100,000 tool calls per month with no credit card, which covers most personal Fish Audio use. Paid plans add higher limits and team features. Your Fish Audio plan and its API limits still apply as usual.

Built-in connectors usually give one AI access to a limited set of apps. Many people use Composio because it lets their AI connect to more apps than it normally supports, or connect to multiple accounts for the same app (e.g. connect Claude to multiple Fish Audio accounts).

With Composio, you connect Fish Audio once and then use it across different AI assistants without setting it up separately in each one. Connect your apps to Composio once, then connect Composio to whichever AI you use, whether that's Claude, ChatGPT, Hermes, or your own custom assistant.

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