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

Input

Text to audio
175/5000
Describe genre, mood, instruments, tempo and the progression from opening to ending. Include “instrumental” when desired and treat any requested length as approximate; our 30-second brief returned 61.6 seconds. at least 1 characters · at most 5000 characters
0/1

Drop files or media links, paste, or browse · 1 file · Max 10 MB · JPG · PNG · WEBP

0 / 1 files
Unsupported by this endpoint; omit image_url from the request. Express the intended visual atmosphere through the music description in prompt. at least 1 characters
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result
0:00 / –:––

Missing the model you need?

GOOGLE TEXT TO MUSIC

Lyria 3.5 API at a glance

Describe the arrangement, hear a stereo MP3, and shape the track around your project.

Billing unit
1 track
Track length does not change the per-track billing unit.
Stereo MP3
44.1 kHz
The supplied test output measured about 193 kbps.
Measured output length
61.6 s
The acoustic folk brief requested 30 seconds at 100 BPM.
Observed generation time
≈30 s
One measured run; allow time to listen and edit afterward.

Results

What you can make with Lyria 3.5

  • 0:00 / –:––

    Prompt-led arrangement

    Put the musical decisions in one brief

    Genre, mood, instruments, tempo, structure and desired length all belong in prompt text. For a podcast cue, name a restrained arrangement and an opening motif; for a video montage, describe how the energy should rise and settle. This gives you concrete details to listen for in the returned track.

    A 62.4-second stereo MP3 from a slow 70 BPM jazz piano brief that asked for about 45 seconds.

  • 0:00 / –:––

    Measured timing

    Plan the cut after hearing the track

    Our acoustic folk test asked for a 30-second instrumental at 100 BPM and returned a 61.6-second MP3 in about 30 seconds. Use that observation to plan an audition and trimming step. It establishes neither an exact-duration control nor a typical processing time across genres.

    A 61.6-second stereo MP3 returned for a 30-second morning folk brief at 100 BPM.

  • Audio delivery

    Bring a stereo MP3 into the project

    Each generation delivers one MP3 track in 44.1 kHz stereo; the supplied test measured about 193 kbps. Check the opening, middle and ending against your creative brief. If a podcast or advertisement has narration, listen to the music beneath that narration before approving the mix.

  • Track-based budgeting

    Budget for variations by track count

    Billing uses the generated track as its unit and does not scale with the track’s length. Consult the displayed rate and decide which prompt variations are worth generating. A shorter length request changes the musical brief without changing the billing unit.

Before you run it

What to know before you run Lyria 3.5

Text to audio
Duration is a prompt instruction rather than a numeric field. Our 30-second request returned 61.6 seconds; trim the downloaded MP3 when a cue must fit an exact timeline.
Text to audio
Google says its music filters block requests for specific artist voices or copyrighted lyrics. Describe instrumentation and musical character, and use text and voices you have the right to use.
All modes
This endpoint accepts a text prompt and returns an MP3; image, format, duration and seed fields are unsupported. Google says Lyria 3.5 audio includes an inaudible SynthID watermark.

Use cases

What to build with the Lyria 3.5 API

  • Background music for a video

    For a hiking montage, request an uplifting acoustic folk instrumental at 100 BPM with picked guitar, light percussion and a gentle ending. Receive one MP3 to audition against the footage and trim to the edit.

  • A podcast opening cue

    For a weekly science podcast, describe a curious electronic instrumental at 90 BPM with rounded synth notes, restrained drums and a short opening motif. The resulting track gives the editor material for an intro beneath the spoken welcome.

  • Music for a game loop

    For a puzzle level, ask for calm ambient music at 80 BPM with soft marimba, sustained pads and a repeating section. Download the MP3, select a usable passage, and check or crossfade the loop boundary in an audio editor.

  • An advertising music bed

    For a home-goods demonstration, request bright instrumental pop at 110 BPM with muted guitar, light bass and sparse percussion. Use the returned MP3 as a candidate music bed and check that it leaves space for the voiceover.

  • A mood sketch before production

    For a quiet nighttime scene, describe a reflective piano instrumental at 70 BPM that opens sparsely and adds warm strings near the end. The track provides a musical direction to review before arranging the final score.

Prompts

Lyria 3.5 prompt examples you can copy

  • Text to audio

    Daylight folk for a walking film

    Create a gentle acoustic folk instrumental for a walking film, hopeful and unhurried, at 100 BPM. Use fingerpicked guitar, warm bass and brushed percussion. Begin with guitar alone, add the rhythm section in the middle, and finish with a soft resolved chord. Aim for a 30-second cue.

    Why it works. The brief names a genre, mood, three instruments and an energy progression that can be checked by ear. Its requested duration is a direction to evaluate after generation.

    Try this prompt
  • Text to audio

    A curious science-podcast intro

    Compose a curious electronic instrumental for a science podcast at 90 BPM. Rounded synth plucks carry a short motif over a soft bass pulse and delicate percussion. Open with the motif, let the pulse enter gently, then thin the arrangement for a spoken introduction. Aim for 30 seconds.

    Why it works. A short motif and thinning arrangement give the editor specific material to audition beneath speech. Tempo stays in the text because there is no separate BPM field.

    Try this prompt
  • Text to audio

    A calm puzzle-room passage

    Generate a calm ambient instrumental for a puzzle game at 80 BPM, with marimba, airy pads and soft hand percussion. Establish a repeating marimba phrase, keep the middle section steady, and return to the opening texture near the end. Aim for one minute with a loop-friendly arrangement.

    Why it works. The repeating phrase and returning texture express a loop intention without promising a seamless file. Check the boundary and make the loop in your editor.

    Try this prompt
  • Text to audio

    Bright music under a product demo

    Make a bright instrumental pop music bed for a home-goods demonstration at 110 BPM. Use muted electric guitar, rounded bass and light claps. Start with a small guitar figure, add a gentle rhythmic lift in the middle, and finish neatly. Keep the arrangement sparse for a voiceover; aim for 45 seconds.

    Why it works. The product context explains why the arrangement should leave space for narration. A defined ending helps focus the listening check before cutting the track.

    Try this prompt
  • Text to audio

    Reflective piano after sunset

    Write a reflective cinematic instrumental at 70 BPM for a quiet scene after sunset. Use felt piano and warm sustained strings. Start with widely spaced piano notes, bring in strings gradually, and return to a quiet piano ending. Aim for a 60-second mood sketch.

    Why it works. The instrument entrance and return give this sketch a clear arc. Compare the result with the scene before deciding whether to revise the prompt.

    Try this prompt
  • Text to audio

    A light jazz opening for a tutorial

    Create a relaxed jazz instrumental for a craft tutorial at 95 BPM. Use clean piano chords, upright bass and brushed snare, with a welcoming mood. Open with a brief piano figure, settle into a restrained repeating groove, and end with the piano figure again. Aim for 30 seconds.

    Why it works. Returning to the opening figure gives the cue a recognizable structure. The restrained groove is a concrete request to assess alongside the tutorial narration.

    Try this prompt

Pricing

Lyria 3.5 API pricing

From $0.12 per request.

Get started

How to use the Lyria 3.5 API in three steps

  1. Step 1

    Define the music brief

    Write a prompt with genre, mood, named instruments, tempo and an opening-to-ending structure. Include a desired length as guidance and say “instrumental” when that is the intended result.

  2. Step 2

    Submit the generation request

    POST to https://api.spicyapi.ai/api/v1/jobs/createTask with bearer authentication and JSON {"model":"google/lyria-3.5/text-to-audio","input":{"prompt":"Calm acoustic folk instrumental, 100 BPM, picked guitar, soft percussion, gentle ending; aim for 30 seconds."}}.

  3. Step 3

    Collect the completed track

    Save data.taskId, then GET /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID using the creating API key. When data.state is succeeded, retrieve the MP3 through data.output.assets[0].url.

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

FAQ

Lyria 3.5 API FAQ

About Lyria 3.5

Build a musical brief around the job the track needs to do: support a spoken introduction, carry a montage, or establish a game scene’s mood. Name the instruments, tempo and energy changes, then generate a track and listen against the actual edit. Lyria 3.5 returns one stereo MP3 per request with billing per track. Keep the observed timing gap in mind: a request for 30 seconds produced 61.6 seconds in our test, so reserve an editing pass for precise length and transitions.

Related models and next tasks