ElevenLabs

Best-in-class text-to-speech and voice cloning. Natural-sounding voices in 30+ languages.

ElevenLabs generates strikingly natural-sounding speech. Use for accessibility, audio versions of content, voice AI apps.

Full walkthrough being written.

Common uses

• Voice AI apps (TTS for AI responses)
• Audio versions of articles / posts
• Voice messages in chat
• Voice cloning for personalized brand voices

Setup

ELEVENLABS_API_KEY in vly secrets. Pick a voice ID from the dashboard or use a default.

const audio = await fetch(`https://api.elevenlabs.io/v1/text-to-speech/${voiceId}`, {
  method: "POST",
  headers: { "xi-api-key": process.env.ELEVENLABS_API_KEY!, "Content-Type": "application/json" },
  body: JSON.stringify({ text, model_id: "eleven_turbo_v2_5" }),
});

Related

Voice AI app recipe

Worked example.

OpenAI TTS

Cheaper alternative.

OpenAI Whisper

The STT counterpart.