ElevenLabs voices in your AI client, on the key that runs every model
ElevenLabs v3, Turbo 2.5 and ElevenLabs Music run through generate on this server: the client sends the text, gets an audio file back as a link, and can pass it to transcribe or to a video model in the next step. No ElevenLabs account; the voices bill per thousand characters from the same balance as every other model.
Add the server to your client
The server is https://api.relayswitch.io/mcp, Streamable HTTP, with your key sent as a Bearer header. Keys start sk-relay-.
Claude Code
claude mcp add --transport http relayswitch https://api.relayswitch.io/mcp \ --header "Authorization: Bearer $RELAYSWITCH_KEY"Then /mcp in Claude Code lists the server and its tools.
Cursor
// .cursor/mcp.json (this project) or ~/.cursor/mcp.json (every project){ "mcpServers": { "relayswitch": { "url": "https://api.relayswitch.io/mcp", "headers": { "Authorization": "Bearer ${env:RELAYSWITCH_KEY}" } } }}Check it from a terminal
curl https://api.relayswitch.io/mcp \ -H "Authorization: Bearer $RELAYSWITCH_KEY" \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}'What the client can call
The tools this page is about. The server lists 15 in all; the rest are on the MCP server page.
| Tool | What it does | Key |
|---|---|---|
media_model | One media model’s settings (every parameter, its values, range and default) and price tiers. | none |
media_quote | What generate would charge for exactly these settings, next to the developer’s price. Nothing runs. | Bearer |
generate | Runs any image, video, speech, music or 3D model and returns the files, a finished image inline. | Bearer |
transcribe | Speech in an audio or video file at a URL to text, or translated into English. | Bearer |
What each call costs, read live
From the catalog at render. The developer’s list price is shown where the catalog has it.
| Model | Setting | Price | Developer’s list |
|---|---|---|---|
| Eleven v3 (text to speech)elevenlabs-v3 | any | $0.10 per 1,000 characters | — |
| Eleven Turbo v2.5 (text to speech)elevenlabs-turbo-2.5 | any | $0.05 per 1,000 characters | — |
| Eleven Musicelevenlabs-music | any | $0.80 per minute | — |
Charged when the model accepts the task; a failed generation is refunded in full.
What to ask once it is connected
Plain requests; the client picks the tool.
- Read this changelog paragraph aloud with elevenlabs-v3 and give me the file.
- Make a 30-second upbeat intro track with elevenlabs-music.
- Check media_model for elevenlabs-turbo-2.5 and list the voices it takes.
ElevenLabs MCP: questions
Setup, models and billing.
Every model as a tool in your AI
From $10 by card or in USDT, USDC, BTC, ETH, SOL. Prepaid, no subscription, no KYC.