Minimax H3 MAX Lipsync API — how to connect and pay

What is Minimax H3 MAX Lipsync

MiniMax H3 Max Lip Sync — a talking video from one photo and a voice track: lips, expression and head motion follow your voice-over, Russian included. Requires image_url (aspect ratio 0.4–2.5) and audio_url (5 seconds to 15 minutes); the clip is as long as the audio. 480p / 768p / 1080p / 2K; enable_transcription transcribes the speech for tighter lips. Priced per second of output video, ×1.2 for clips over 15 s.

Example request

Pass your key in the Bearer header. The API returns jobId for polling the status.

curl -sS https://getvibeapi.com/api/media/generate \
  -H "Authorization: Bearer $GETVIBE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary '{"model":"minimax-h3-max-lipsync","prompt":"Describe the desired result","opts":{}}'

JavaScript

const response = await fetch('https://getvibeapi.com/api/media/generate', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.GETVIBE_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "minimax-h3-max-lipsync",
  "prompt": "Describe the desired result",
  "opts": {}
}),
});

if (!response.ok) throw new Error(`GetVibe API: ${response.status}`);
const { jobId } = await response.json();
console.log(jobId);