Skip to main content

Lyria 3.5 API

google/lyria-3.5/text-to-audio

Google DeepMind’s Lyria 3.5 text-to-audio endpoint generates a music track from a written brief. Send genre, mood, instruments, tempo and structure in prompt to receive one stereo MP3.

From $0.12/request

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • 0:00 / –:––
    Bright acoustic folk instrumental at 100 BPM

    A neutral acoustic folk instrumental brief requested 30 seconds at 100 BPM. The measured result was a 61.6-second MP3, 44.1 kHz stereo at about 193 kbps, generated in approximately 30 seconds.

  • 0:00 / –:––
    Slow late-night jazz piano instrumental

    The brief named solo piano, brushed drums, upright bass, a gentle swing at 70 BPM and roughly 45 seconds; the track came back at 62.4 seconds, 44.1 kHz stereo and about 192 kbps.

This example starts at $0.12 per request. The Playground updates the estimate when you change the settings.