GPT Image 2.5 is LIVE — Flare & Sunburst | Try in Image Generator →

google/

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.

text-to-audio
Input
Enable Safety Checker

Idle

$0.1per run·~10 / $1

ExamplesView all

Cinematic electronic pop with emotional female vocals, soft piano intro, atmospheric synth pads, deep bass, crisp modern drums, and subtle orchestral strings. The song begins intimate and restrained, gradually building into a powerful uplifting chorus with wide harmonies and a memorable melodic hook. Bittersweet but hopeful mood, polished production, dramatic dynamics, modern soundtrack feel, suitable for a night-drive movie scene.

Related Models

README

Google Lyria 3.5

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.

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

ParameterRequiredDescription
promptYes1-5,000 characters. Description of the song: genre, mood, tempo, instruments, vocal style. Include your own lyrics with section tags, or write "instrumental" for no vocals.
imageNoReference image to guide the mood and atmosphere of the generated song.

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

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Lyria 3.5 Music API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/google/lyria-3.5/music with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Lyria 3.5 Music below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light"
}
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 "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$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
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/google/lyria-3.5/music";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/google/lyria-3.5/music", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout", "deleted"}:
        raise RuntimeError(result)
    time.sleep(2)

Lyria 3.5 Music API — Frequently asked questions

What is the Lyria 3.5 Music API?

Lyria 3.5 Music is a Google model for audio generation, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Lyria 3.5 Music API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/google/google-lyria-3.5-music.

How much does Lyria 3.5 Music cost per run?

Lyria 3.5 Music starts at $0.1 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Lyria 3.5 Music accept?

Key inputs: `prompt`, `image`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/google/google-lyria-3.5-music.

How do I get started with the Lyria 3.5 Music API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Lyria 3.5 Music outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Google). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.