Skip to content

ElevenLabs

Updated View as Markdown

Find available ElevenLabs voices. Generate a short approved narration.

Example workflows

Copy a prompt into your connected AI client after connecting this integration. Choose resources you can access and review the supported command before running it.

Find available ElevenLabs voices

Help me with this task in ElevenLabs: Find available ElevenLabs voices. Ask me for any required inputs and confirm the resources and scope before calling the command. Read one response page. Turn the returned data into a concise working summary with original IDs, dates and source links when available. Separate missing information from confirmed results and tell me whether more pages remain. Do not invent fields or change data.

Explore this command: elevenlabs.voices.list

Narrate an approved update

First ask me to select a voice I am permitted to use. Prepare a narration of at most 200 characters from the approved rollout update. Show its exact text before generation. After I approve, use eleven_flash_v2_5 and mp3_22050_32 to create one MP3. Return the audio once; do not clone a voice, generate alternatives or retry an uncertain result.

Explore this command: elevenlabs.speech.create

What you can do (2)

What you can do

Available commands: 2 (1 read, 1 write). Enable only the commands your application needs.

Command Effect
Find available ElevenLabs voices — elevenlabs.voices.list Read
Generate a short approved narration — elevenlabs.speech.create Write

Connect and use

Connect and use

This connection uses your provider account.

Connect this integration, enter your provider credentials, choose commands and save. Complete provider authorization if prompted.

Get your provider credentials

Follow these steps for ElevenLabs, then enter the issued values in the connection form below.

  1. ElevenLabs API key with voice and text-to-speech permissions. Voice rights and provider credits apply. Audio generation accepts at most 200 characters and returns a single bounded MP3; no voice cloning. Open the official API documentation, create credentials limited to this workflow, then enter the values shown below. Select only the commands you need. Revoking credentials at the provider disconnects access.

Official credential setup

Where to enter credentials

In the integration page, sign in, choose your workspace and open Connect. If a Credentials choice is shown, select Use my credentials. Fill the following connection fields and save. Provider credentials belong in this form, never in an MCP configuration or tool input.

Connection field Requirement
ElevenLabs API key Required

Open API keys and create a Tooluse.net key for the enabled commands.

Set TOOLUSE_API_KEY in your client and use the shared MCP configuration.

Configure Claude Code, Codex or Cursor once

Permissions and results

If you have more than one workspace, check the selected workspace in the connection or API-key dialog before saving. Roles, enabled commands, expiry and revocation use Tooluse.net's existing permissions. Disabling a connection or revoking a key immediately prevents new calls.

Send one Claude tool_use block per request. Keep the same Idempotency-Key when retrying the same request; use a new key for a new call. The response includes the shared Tooluse.net receipt and Claude tool_result. Check both HTTP status and the returned tool result before treating a call as successful.

Your connection's daily allowance and key permissions also apply. Adding a connection does not make a provider request.

Calls return the shared execution receipt and a Claude tool_result. Provider output varies by operation; consult the provider documentation for its response fields. Unconfirmed calls should be checked before retrying.

Call from your client

Use the shared MCP configuration. Refresh your client's tool list after saving the connection or changing key permissions, then call the returned tool name with the example input below.

Configure Claude Code, Codex or Cursor once

Discover your enabled tools

List permitted tools in Claude format. Read every page using page and size (maximum 100) until all results have been received. Use the returned name, not a catalog capability identifier, in the tool_use block.

curl 'https://api.tooluse.net/v1/tools' \
  -H "Authorization: Bearer $TOOLUSE_API_KEY"

Find this command in the tool list permitted by your key. Replace svc_FROM_YOUR_TOOL_LIST with its returned name. Use a new Idempotency-Key for each new call and retain it when retrying that same call.

HTTP call

curl 'https://api.tooluse.net/v1/tool-calls' \
  -H "Authorization: Bearer $TOOLUSE_API_KEY" \
  -H 'Content-Type: application/json' \
  -H 'Idempotency-Key: replace-with-a-new-call-id' \
  --data '{
  "type": "tool_use",
  "id": "toolu_example",
  "name": "svc_FROM_YOUR_TOOL_LIST",
  "input": {}
}'

Send one Claude tool_use block per request. Keep the same Idempotency-Key when retrying the same request; use a new key for a new call. The response includes the shared Tooluse.net receipt and Claude tool_result. Check both HTTP status and the returned tool result before treating a call as successful.

Commands

Find available ElevenLabs voices — elevenlabs.voices.list

Find available ElevenLabs voices. One explicit provider request; no retries or automatic follow-up pages. Customer permissions and quotas apply.

This is a read operation. Provider rate limits and data access rules still apply.

Connect and use

Parameters

Requiredness is local to the containing object. A required child is required only when its parent object or array item is provided. Alternative schemas are identified in the Constraints column; the linked full JSON Schema is authoritative.

This tool has no input parameters.

Full JSON Schema

Full JSON Schema

Example input

{}

At most 1 provider requests per invocation; timeout: 30 seconds.

Generate a short approved narration — elevenlabs.speech.create

Generate a short approved narration. One explicit provider request; no retries or automatic follow-up pages. Customer permissions and quotas apply.

This operation can change provider data. Review the input before allowing an agent to call it.

Connect and use

Parameters

Requiredness is local to the containing object. A required child is required only when its parent object or array item is provided. Alternative schemas are identified in the Constraints column; the linked full JSON Schema is authoritative.

Parameter Type Required in parent Description Constraints
path object Required additionalProperties: false
path.voice_id string Required minLength: 1; maxLength: 100
query object Required additionalProperties: false
query.output_format string Required enum: ["mp3_22050_32"]
body object Required additionalProperties: false
body.text string Required minLength: 1; maxLength: 200
body.model_id string Required enum: ["eleven_flash_v2_5"]

Full JSON Schema

Full JSON Schema

Example input

{
  "path": {
    "voice_id": "voice1"
  },
  "query": {
    "output_format": "mp3_22050_32"
  },
  "body": {
    "text": "Your account handoff is ready for review.",
    "model_id": "eleven_flash_v2_5"
  }
}

At most 1 provider requests per invocation; timeout: 30 seconds.

Errors

Check the key's expiry, revocation, workspace and allowed operations.

Reuse the same idempotency key only for the same request.

The connection or provider limit has been reached. Check the receipt before retrying.

Test the connection

Open the integration's commands below to inspect parameters and examples. Start with a read command for an account or resource you can access. Refresh your client's tool list, use the returned tool name, and check the execution result and usage. Provider charges and permissions still apply. Never test a write against production data without reviewing it.

Official provider documentation

Type to search…

↑↓ navigate↵ selectEsc close