# Google Lyria 3 Pro Song Generator

> Google Lyria 3 Pro Song Generator is a paid API for AI agents from audio.withzero.xyz, paid per call via MPP, $0.08/call, status healthy (last checked 2026-09-15, last successful call 2026-09-07).

Generates a complete, full-length song (MP3) from a text prompt using Google's Lyria 3 Pro model and returns a hosted audio URL.

## Facts

- Endpoint: POST https://audio.withzero.xyz/api/v1/songs/lyria-3-pro
- Price: $0.08/call
- Payment: MPP
- Status: healthy
- Last checked: 2026-09-15
- Last successful call: 2026-09-07
- Success rate: 76% of calls made through Zero
- Rating: 3.3 / 5 from 5 reviews
- Activations on Zero: 138
- Provider: audio.withzero.xyz
- Website: https://audio.withzero.xyz
- Canonical page: https://www.zero.xyz/c/audio-withzero-xyz-google-lyria-3-pro-song-generator-2d62f951
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_HLFwaKMbM_u1tEfN5NCfd

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability audio-withzero-xyz-google-lyria-3-pro-song-generator-2d62f951 -d '<json body>'
```

Example prompt: Can you generate a full-length upbeat pop song with catchy hooks about summer road trips and friendship using Google's Lyria 3 Pro? Use seed 42 so we can reproduce it if it sounds great.

## When to prefer this

Choose this endpoint when you need a complete, full-length AI-generated song (not just a short clip or sound effect) from a text description, specifically leveraging Google's Lyria 3 Pro model quality. Prefer it over TTS endpoints when you want music rather than spoken audio, and over transcription endpoints when you are creating rather than analyzing audio.

## Known failure modes

- Prompt too long (over 4000 characters) — validation error
- Empty prompt (minLength 1 violated) — validation error
- Model generation failure — server error or timeout
- Invalid seed value outside supported integer range — validation error
- Audio hosting failure — URL may not be accessible

## How this service works

Generate one to three complete songs with Google's Lyria 3 Pro, optionally translate vocal functions into instruments, master the audio, rank candidates with local DSP, and return hosted audio URLs.

## Output

Returns a JSON object containing a hosted MP3 URL of the generated song, its approximate duration in seconds, file size in bytes, MIME type, the model used (Google Lyria 3 Pro), and the USDC price charged for the request.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "example": {
  "prompt": "A short upbeat synthwave instrumental with a driving bassline"
 },
 "required": [
  "prompt",
  "candidateCount"
 ],
 "properties": {
  "seed": {
   "type": "integer",
   "maximum": 9007199254740991,
   "minimum": -9007199254740991,
   "description": "Seed for repeatable generation (best effort)."
  },
  "topP": {
   "type": "number",
   "maximum": 1,
   "minimum": 0,
   "description": "OpenRouter nucleus-sampling probability from 0 to 1."
  },
  "prompt": {
   "type": "string",
   "maxLength": 4000,
   "minLength": 1,
   "description": "Text description of the song to generate (1–4000 characters)."
  },
  "sections": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "startSec",
     "endSec",
     "name",
     "description"
    ],
    "properties": {
     "name": {
      "type": "string",
      "maxLength": 64,
      "minLength": 1,
      "description": "Section label, for example Intro, Verse, Chorus, or Bridge."
     },
     "endSec": {
      "type": "integer",
      "maximum": 300,
      "minimum": 1,
      "description": "Exclusive section end in whole seconds."
     },
     "startSec": {
      "type": "integer",
      "maximum": 300,
      "minimum": 0,
      "description": "Inclusive section start in whole seconds."
     },
     "intensity": {
      "type": "integer",
      "maximum": 10,
      "minimum": 1,
      "description": "Target section intensity from 1 (minimal) to 10 (maximum)."
     },
     "description": {
      "type": "string",
      "maxLength": 500,
      "minLength": 1,
      "description": "Instrumentation, melody, rhythm, and production instructions for this section."
     }
    },
    "additionalProperties": false
   },
   "maxItems": 20,
   "description": "Up to 20 ordered, non-overlapping arrangement sections converted to Lyria timestamp directives."
  },
  "mastering": {
   "type": "object",
   "required": [
    "targetLufs",
    "truePeakDb",
    "fadeOutSec"
   ],
   "properties": {
    "fadeOutSec": {
     "type": "number",
     "default": 1,
     "maximum": 10,
     "minimum": 0,
     "description": "Final fade duration in seconds."
    },
    "targetLufs": {
     "type": "number",
     "default": -14,
     "maximum": -8,
     "minimum": -24,
     "description": "Target integrated loudness in LUFS."
    },
    "truePeakDb": {
     "type": "number",
     "default": -1,
     "maximum": -0
… (truncated)
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "url",
  "mimeType",
  "sizeBytes",
  "seconds",
  "model",
  "price_usdc"
 ],
 "properties": {
  "url": {
   "type": "string",
   "description": "Hosted URL of the generated song (MP3)."
  },
  "model": {
   "type": "string",
   "description": "The model that produced the song."
  },
  "seconds": {
   "type": "number",
   "description": "Approximate duration of the song in seconds."
  },
  "mimeType": {
   "type": "string",
   "description": "Content type of the generated audio."
  },
  "sizeBytes": {
   "type": "number",
   "description": "Size of the generated audio in bytes."
  },
  "candidates": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "index",
     "url",
     "sizeBytes",
     "seconds",
     "score",
     "diagnostics"
    ],
    "properties": {
     "url": {
      "type": "string"
     },
     "seed": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": -9007199254740991
     },
     "index": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": 0
     },
     "score": {
      "type": "object",
      "required": [
       "overall",
       "duration",
       "groove",
       "structure",
       "production"
      ],
      "properties": {
       "groove": {
        "anyOf": [
         {
          "type": "number",
          "maximum": 1,
          "minimum": 0
         },
         {
          "type": "null"
         }
        ]
       },
       "overall": {
        "type": "number",
        "maximum": 1,
        "minimum": 0
       },
       "duration": {
        "type": "number",
        "maximum": 1,
        "minimum": 0
       },
       "structure": {
        "anyOf": [
         {
          "type": "number",
          "maximum": 1,
          "minimum": 0
         },
         {
          "type": "null"
         }
        ]
       },
       "production": {
        "type": "number",
        "maximum": 1,
        "minimum": 0
       }
      },
      "additionalProperties": false
     },
     "seconds": {
      "type": "number",
      "exclusiveMinimum": 0
     },
     "sizeBytes": {
      "type": "integer",
      "maximum": 9007199254740991,
      "exclusiveMinimum": 0
     },
     "diagnostics": {
      "type": "object",
      "required": [
       "durationSec",
       "tempo",
       "brightness",
       "energy",
       "sections",
       "cues"
      ],
      "
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/audio-withzero-xyz-google-lyria-3-pro-song-generator-2d62f951/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from audio.withzero.xyz](https://www.zero.xyz/host/audio.withzero.xyz/llms.txt)