How to integrate AllModels MCP with Atomic Agent

Connect Atomic Agent to AllModels MCP. Convert product announcements to natural speech, transcribe customer support call recordings, and more using natural language, with authentication handled for you.

AllModels logoAllModels
Api Key

AllModels is a unified API for text-to-speech, speech-to-text, realtime voice, and voice cloning across AI providers. It gives developers one consistent way to build and manage voice features.

40 Tools

Introduction

Atomic Agent is an open-source AI agent that runs on your machine and supports local models through llama.cpp. Connect it to 1,700+ apps through Composio, including AllModels.

This guide uses Atomic Agent's built-in Composio integration. You need Atomic Agent v0.5.6 or later, your own Composio API key, and a AllModels account. See the Atomic Agent documentation for installation instructions.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate AllModels with

How Atomic Agent connects to AllModels

Atomic Agent connects to Composio's Tool Router over Streamable HTTP MCP. It discovers the tools needed for your request, and Composio handles account authentication.

Execution and account-connection tools follow Atomic Agent's configured approval policy. Review any approval prompt before allowing an action on your connected account.

Connect AllModels to Atomic Agent

  1. Sign up or sign in to the Composio dashboard. Copy your API key.
  2. In Atomic Agent, open the Integrations tab and select Composio. Select API key, press e, paste the key, and press Enter. The tools become available immediately, without a restart.
  3. Ask Atomic Agent to do something in AllModels. It searches Composio for the right tool.
  4. On first use, open the sign-in link returned in the chat. Connect your AllModels account, then return to Atomic Agent to continue.

Headless setup

Add the following line to ~/.atomic-agent/.env, replacing YOUR_COMPOSIO_API_KEY with your key. Start Atomic Agent after saving the file.

bash
COMPOSIO_API_KEY=YOUR_COMPOSIO_API_KEY

What is the AllModels MCP server, and what's possible with it?

The AllModels MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your AllModels account. It provides structured and secure access to unified text-to-speech, speech-to-text, realtime voice, voice cloning, and account tools, so your agent can generate speech, transcribe audio, find models and voices, manage voice and realtime configurations, and review account activity on your behalf.

  • Speech generation and transcription: Have your agent turn text into audio with OpenAI-compatible or ElevenLabs-compatible tools, or transcribe uploaded audio into text and timing data.
  • Voice and model discovery: Let the agent search public voices, browse provider voices, and list available speech models with their supported capabilities and pricing.
  • Voice cloning management: Direct your agent to create, inspect, list, download samples for, or delete organization-owned cloned voices.
  • Realtime voice configuration: Instruct your agent to create, update, inspect, list, or delete realtime profiles and Speech Engines for conversational audio workflows.
  • Account monitoring: Have your agent check API health, balance, usage, activity, transactions, and available credits, or create a top-up payment link when funds need to be added.

Use AllModels from Atomic Agent

With your account connected, ask Atomic Agent to work with AllModels in natural language. You can connect more apps through the same Composio integration as you need them.

Visit the Atomic Agent website or inspect the Atomic Agent source code.

Troubleshooting

Why is my API key rejected?

Copy the key directly from the Composio dashboard. Atomic Agent requires ASCII characters because it sends the key in an HTTP header. Remove any extra characters introduced when copying.

Why are Composio tools unavailable after saving a key?

Check that you use Atomic Agent v0.5.6 or later and that Composio is enabled in your configuration. A "composio": { "enabled": false } setting disables the integration while keeping the saved key on disk.

Does Composio have a free plan?

The Hobby plan includes 100,000 tool calls per month. Composio-managed OAuth apps have a lower included allowance. See Composio pricing for the current limits that apply to your connection.

TOOLS

Supported Tools

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

Add SDK Voice

Clone one voice through the ElevenLabs voices.add compatibility endpoint.

Create Custom Voice

Clone a voice from an uploaded recording.

Create Realtime Client Secret

Create a short-lived, single-use client secret and direct WebSocket URL from exactly one saved profile ID or complete inline profile.

Create Realtime Profile

Create a reusable Realtime speech pipeline or direct speech-to-speech profile with model routing, audio, conversation, client, lifecycle, limits, and tags.

Create Speech Engine

Create a reusable Speech Engine that connects client audio to speech-to-text, an application WebSocket, and synthesized responses.

Create Speech Engine Signed URL

Create a short-lived, single-use WebSocket URL that lets one client connect to an existing Speech Engine without receiving the account API key.

Create Top-Up Link

Create an expiring payment checkout link for adding a specified USD amount to the connected AllModels account.

Delete Custom Voice

Permanently delete an organization-owned cloned voice by voice_id.

Delete Realtime Profile

Permanently delete a saved Realtime profile by profile_id.

Delete SDK Voice

Permanently delete an organization-owned cloned voice through the ElevenLabs voices.delete compatibility endpoint.

Delete Speech Engine

Permanently delete a Speech Engine so it can no longer issue new signed conversation URLs.

Download Custom Voice Sample

Download the audio sample authorized by a short-lived custom-voice cloning token.

Generate OpenAI Speech

Generate speech through AllModels' OpenAI-compatible endpoint.

Generate SDK Speech

Generate a complete audio file through AllModels' ElevenLabs-compatible textToSpeech.convert endpoint.

Get Account Balance

Return the connected account's paid and spendable credits, USD balance, availability state, and monthly-billing fields when present.

Get Account Usage

Return daily API-key usage and aggregate request, credit, and USD cost totals for a range of at most 90 days, optionally filtered by provider, model, or capability.

Get Custom Voice

Return one organization-owned cloned voice, its readiness status, supported models, and provider status by voice_id.

Get OpenAI Credits

Return available account funds in the OpenRouter-compatible credits envelope used by OpenAI-style clients.

Get Provider Skill

Return the provider-specific Markdown guide for steering TTS delivery through AllModels.

Get Realtime Profile

Return one saved pipeline or speech-to-speech Realtime profile by its profile_id, including the complete nested configuration.

Get SDK Voice

Return one organization-owned cloned voice through the ElevenLabs voices.get compatibility endpoint.

Get Speech Engine

Return one Speech Engine configuration by its speech_engine_id.

Check API Health

Check whether the AllModels API and its LLM dependency are available, including nullable deployment commit identifiers.

List Account Activity

List individual API requests made with the connected API key, newest first, with time, provider, model, capability, and status filters plus an opaque continuation cursor.

List Account Transactions

List organization credit events such as top-ups, grants, refunds, adjustments, and expirations, returning one page and an opaque continuation cursor.

List Custom Voices

List the organization's cloned voices across projects, newest first by default, returning one cursor-controlled page.

List Models

List available TTS, STT, and speech-to-speech models with aliases, provider capabilities, endpoints, instruction support, and pricing.

List Providers

List providers keyed by provider ID with their default models and voices, supported TTS/STT models, formats, capabilities, and pricing.

List Realtime Profiles

List saved Realtime profiles with name search, sort direction, and one cursor-controlled page.

List SDK Voices

List voices from one TTS provider in the ElevenLabs voices.get_all compatibility envelope.

List Speech Engines

List permanent Speech Engines with name search, sort controls, and one cursor-controlled page.

Search SDK Voices

List voices for one text-to-speech provider in the ElevenLabs SDK search compatibility envelope, optionally limiting the single returned page.

Search Voices

Search the public voice catalogue by text, model, provider, language, category, labels, and sort order, returning one cursor-controlled page.

Start Agent Signup

Send a six-digit AllModels access code to an account owner's email address.

Stream SDK Speech

Generate speech through the ElevenLabs-compatible streaming HTTP endpoint and return the produced audio as a downloadable file.

Transcribe OpenAI Audio

Transcribe an uploaded audio file through AllModels' OpenAI-compatible endpoint and preserve JSON, text, subtitle, or SSE output.

Transcribe SDK Audio

Transcribe an uploaded audio file through AllModels' ElevenLabs-compatible endpoint and return text, language, and available word or character timing.

Update Realtime Profile

Patch selected fields of a saved pipeline or speech-to-speech Realtime profile.

Update Speech Engine

Partially update an existing AllModels Speech Engine.

Verify Agent Signup

Verify an emailed six-digit AllModels signup code using the same email address that requested it.

FAQ

Frequently asked questions

Start with AllModels.It takes 30 seconds.

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

Start building