ToolsIntegrations

elevenlabs

ElevenLabs text-to-speech — high-quality voices in 30+ languages. For narration, voice agents, IVR flows.

import { elevenlabs } from '@agentskit/tools'

const runtime = createRuntime({
  adapter,
  tools: [...elevenlabs({ apiKey: process.env.ELEVENLABS_API_KEY! })],
})

#Sub-tools

Name	Purpose
`elevenlabsTts`	Convert text to audio (returns buffer + content-type)

Bundled: elevenlabs(config).

#Config

type ElevenLabsConfig = {
  apiKey: string
  defaultVoiceId?: string
  modelId?: string          // e.g. 'eleven_multilingual_v2'
  fetch?: typeof fetch
}

#Example — narrate a digest

const runtime = createRuntime({
  adapter,
  tools: [
    ...elevenlabs({ apiKey, defaultVoiceId: '21m00Tcm4TlvDq8ikWAM' }),
    ...s3({ client, bucket: 'podcast-output' }),
  ],
})

await runtime.run('Summarize today\'s PRs, narrate with ElevenLabs, save MP3 to S3.')

Integrations overview · whisper · deepgram — STT pairs.
Issue #479 — voice mode component.

Explore nearby

✎ Edit this page on GitHub·Found a problem? Open an issue →·How to contribute →

openaiImages

OpenAI Images API (DALL-E / gpt-image) — generate images from prompts.

whisper

OpenAI Whisper — speech-to-text for audio transcription. 99 languages.

On this page

Sub-tools Config Example — narrate a digest Related