Google Lyria 3.5 Music API Documentation

Google Lyria 3.5 Music API Documentation

Playground

Google Lyria 3.5 generates full-length songs up to about three minutes with expressive vocals, timed lyrics, and complete arrangements from text prompts and optional image input. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Google Lyria 3.5 is Google’s flagship music generation model for full-length songs. Describe the track you want in natural language — genre, mood, tempo, instruments, vocal style — and get a complete song of up to about three minutes with expressive vocals, timed lyrics, and a full arrangement with verses, choruses, and bridges. Write your own lyrics with section tags, or ask for an instrumental. Optionally guide the mood with a reference image.

• Need a short loop or preview instead? Try Google Lyria 3 Clip

Why Choose This?

• Full-length songs Complete tracks of up to about three minutes with coherent structure — intro, verses, choruses, bridges, and outro.

• Expressive vocals and timed lyrics Richer musical arrangements and more natural vocals than Lyria 3 Pro, with lyrics that follow your text closely.

• Bring your own lyrics Add [Verse], [Chorus], and [Bridge] tags in the prompt to control the song structure, or add timestamps such as [0:00 - 0:10] Intro to shape the timeline.

• Multilingual Write the prompt in the language you want the song sung in; the vocal style adapts to the language.

• Image-guided generation Upload a reference image to inspire the musical mood and atmosphere.

Parameters

How to Use

1. Write your prompt — describe the genre, tempo, instruments, mood, and vocal style.
2. Add lyrics (optional) — paste your lyrics with [Verse] / [Chorus] / [Bridge] tags, or add timestamps to control when sections start.
3. Upload a reference image (optional) — provide an image to inspire the musical atmosphere.
4. Submit — generate and download your song as an MP3.

Pricing

$0.10 per generated song. Billed per generation, not per second or token.

Best Use Cases

• Original songs — Produce complete vocal tracks for short films, ads, social content, and demos.
• Film & Video Scoring — Generate full-length music beds and underscore for video productions.
• Game & Interactive Media — Create atmospheric tracks and theme songs for games and apps.
• Podcast & Streaming — Generate intro, outro, and background music with or without vocals.
• Creative Production — Rapidly prototype song ideas, lyrics, and styles before studio work.

Pro Tips

• Be specific about BPM, key instruments, vocal gender or style, and energy level for the most accurate results.
• Use section tags to control structure; without them the model writes its own lyrics from your description.
• Say how long the song should be in the prompt (for example, “a two-minute song”) to control duration.
• Try pairing an atmospheric image with a minimal prompt to let the image drive the mood.
• Requests for a specific artist’s voice or copyrighted lyrics are blocked by Google’s content policy.

Notes

• Only prompt is required (1-5,000 characters); image is optional.
• Duration is guided by the prompt, not an exact duration parameter. negative_prompt, seed, and output-format selection are not exposed.
• The WaveSpeed result provides the generated MP3 URL in outputs; a separate lyrics response is not part of this endpoint contract.
• Output is a 44.1 kHz stereo MP3. Every song carries an inaudible SynthID watermark.
• Generation is not deterministic; identical prompts produce different songs.
• Please ensure your content complies with Google’s usage policies.

Related Models

• Google Lyria 3 Pro — Previous-generation full-length music model.
• Google Lyria 3 Clip — 30-second clips at faster generate speed.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/lyria-3.5/music" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters