Skip to content
  1. Developers
  2. Models
  3. Speech
By xAI, served by VidmoatAvailable

Grok TTS

xAI's text-to-speech. Five voices, any language, adjustable speed. What auto picks first.

id provider "grok"

Sample

Waveform of the Grok TTS sample, voice eve

Text Welcome to Vidmoat. Describe the edit you want, and watch it happen.

A real, unedited output of this model, made for this page.

What it does well

  • Voices: eve, ara, leo, rex and sal.
  • Speed 0.7x to 1.5x.

Limits

  • 1,000 characters per clip; longer text is cut and the response says where.

Where to call it

REST APIPOST /v1/ai/speechMCPgenerate_speech
Editor agentgenerateMedia kind "speech"
Chat botsTelegram, WhatsApp and Discord
Vidmoat appVidmoat editor

Try it

curl
curl -X POST https://api.vidmoat.com/v1/ai/speech \
  -H "Authorization: Bearer $VIDMOAT_KEY" \
  -H "Content-Type: application/json" \
  -d '{"provider":"grok","text":"Three things nobody tells you about sourdough.","voiceId":"eve"}'

A test key answers with a sample and spends nothing. Every parameter and error is in the API reference.

Read more