ElevenLabs

What you can do

3 actions, each one call from a workflow or a server function. Triggers come from your app: a row changing, a schedule or a webhook.

• Speech to Textelevenlabs-speech-to-text
  Transcribe audio to text using ElevenLabs Scribe. Returns the transcribed text string.
• Text to Speech (Free Tier)elevenlabs-text-to-speech
  Convert text to speech using ElevenLabs free tier model (non-streaming, cost-effective). Returns an audio URL.
• Custom API Callcustom_api_call
  Check [Elevenlabs API reference](https://elevenlabs.io/docs/api-reference/introduction) for the list of available endpoints.

Set it up

About two minutes, once per project or once for the whole workspace.

1. Open Integrations in the builder

   Backend panel, Integrations tab, then ElevenLabs. To connect it for every project, use Workspace settings, Integrations.

2. Add your credentials

   Fill in the fields the provider needs (listed below). They are stored encrypted in the vault.

   • Region Select your ElevenLabs account region
   • API Key Your ElevenLabs API key. Required permissions: user:read, text_to_speech, voices:read, models
3. Call an action

   From a workflow, by integration id and action name. The call answers with success, output and, when it fails, the reason.

   // .workflow.js (native ctx)
   export async function run(ctx) {
     const res = await ctx.integrations.invoke("elevenlabs", "elevenlabs-speech-to-text", {
       "audioBase64": "<audio (base64)>"
     });
     if (!res.success) throw new Error(res.error);
     ctx.log.info("ElevenLabs answered", { output: res.output });
   }

More in AI and ML

• ABAmazon Bedrock
• AOAzure OpenAI
• Claude
• CoCohere
• Deepgram
• DeepSeek
• All of AI and ML