# Lyria API

> Provider: **Google**
> Source: https://www.pixazo.ai/models/lyria

Google's advanced AI music generation model for creating high-quality audio content.

## Lyria 2

### Text to Music

## Base URL

```
https://gateway.pixazo.ai/lyria-2/v1
```

## Authentication

All requests require an API key passed via header.

Header

Type

Required

Description

Ocp-Apim-Subscription-Key

string

Yes

Your API subscription key

## Music Request - Lyria 2

## Request Code

HTTP Python JavaScript cURL

```
POST https://gateway.pixazo.ai/lyria-2/v1/lyria-2/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "prompt": "Futuristic country music, steel guitar, huge 808s"
}
```

```
import requests

url = "https://gateway.pixazo.ai/lyria-2/v1/lyria-2/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "prompt": "Futuristic country music, steel guitar, huge 808s"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
```

```
const url = 'https://gateway.pixazo.ai/lyria-2/v1/lyria-2/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_API_KEY'
};
const data = {
  prompt: 'Futuristic country music, steel guitar, huge 808s'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
```

```
curl -X POST "https://gateway.pixazo.ai/lyria-2/v1/lyria-2/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "prompt": "Futuristic country music, steel guitar, huge 808s"
  }'
```

## Output

```
{
  "request_id": "lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

[Try Now](https://api.pixazo.ai/api-details#api=lyria-2&operation=music-request)

## Webhook (Optional)

Add the `X-Webhook-URL` header to your submit request to receive a `POST` callback when the job completes — no polling required.

### Webhook Headers

Header

Required

Default

Description

`X-Webhook-URL`

Yes (to enable)

—

HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).

`X-Webhook-Mode`

No

`terminal`

`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at **15s** for tighter progress updates.

### Example: enable webhook

```
X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal
```

### Callback Payload

Your endpoint receives a `POST application/json` with the same shape as the `GET /v2/requests/status/{request_id}` response. Example terminal callback (mode `terminal`):

```
{
  "request_id": "lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "lyria-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.wav"
    ],
    "media_type": "audio/wav"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}
```

### Failure callback shape

```
{
  "request_id": "lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lyria-2",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}
```

### Delivery semantics

-   **terminal mode (default)** — exactly one `POST` when the request reaches a terminal status. No callback during `PROCESSING`.
-   **sync mode** — `POST` on every status poll (with delay capped at ~15s) plus a final `POST` at terminal status. Use when you want progress updates.
-   **Idempotency** — use `request_id` as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
-   **Response** — respond `200 OK` within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
-   **HTTPS required** — plain `http://` URLs are rejected.

## Request Parameters - Music Request

Parameter

Required

Type

Default

Allowed values / range

Description

prompt

Yes

string

—

—

Text prompt describing the music to generate

negative\_prompt

No

string

—

—

Description of what to exclude from the generated audio

seed

No

integer

—

—

Random seed for reproducible generation

## Example Request

```
{
  "prompt": "Futuristic country music, steel guitar, huge 808s, synth wave elements space western cosmic twang soaring vocals",
  "negative_prompt": "low quality, distorted, noise, static, vocals out of tune",
  "seed": 42
}
```

## Response

```
{
  "request_id": "lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

## Request Headers

Header

Value

Content-Type

application/json

Cache-Control

no-cache

Ocp-Apim-Subscription-Key

Your API subscription key

## Response Handling

Common status codes.

Code

Meaning

202

Accepted — Request queued

400

Bad Request

401

Unauthorized

402

Insufficient Balance

403

Forbidden

429

Too Many Requests

500

Internal Server Error

## Error Responses

Queue system errors and model validation errors.

### Queue System Errors

```
// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}
```

```
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'lyria-2' not found or is disabled"
}
```

### Error via Status/Webhook

```
{
  "request_id": "lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lyria-2",
  "error": "Description of the error",
  "output": null
}
```

## Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

### Endpoint

```
GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY
```

## cURL Example

```
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
```

## Response (Completed)

```
{
  "request_id": "lyria-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "lyria-2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lyria-2_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}
```

## Response Fields

Field

Type

Description

request\_id

string

Unique request identifier

status

string

QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR

model\_id

string

Model that processed the request

error

string|null

Error message if failed

output.media\_url

array

URLs to generated media (R2 CDN)

output.media\_type

string

MIME type of the output

created\_at

string

When request was created

completed\_at

string|null

When request completed

polling\_url

string

Status URL (initial response only)

## Status Values

Status

Description

QUEUED

Request accepted, waiting to be processed

PROCESSING

Being processed by the model

COMPLETED

Done — output contains the result

FAILED

Failed — check error field

ERROR

System error — not charged

## Status Flow

```
QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR
```

## Typical Workflow

1.  **Send a generate request** to the API endpoint
2.  **Save the `request_id`** from the response
3.  **Poll** every 5-10 seconds: `GET /v2/requests/status/{request_id}`
4.  **When `status` is `"COMPLETED"`**, download from `output.media_url`

**Tip:** Use `X-Webhook-URL` header to get a callback instead of polling.

## Lyria 3

### Text to Music

## Endpoint URL

```
POST https://gateway.pixazo.ai/lyria-3/v1/lyria-3/generate
```

## Authentication

All requests require an API key passed via header.

Header

Type

Required

Description

Ocp-Apim-Subscription-Key

string

Yes

Your API subscription key

## Text to Music - Lyria 3

## Request Code

HTTP Python JavaScript cURL

```
POST https://gateway.pixazo.ai/lyria-3/v1/lyria-3/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A calm acoustic folk song with gentle guitar and soft strings. Instrumental only."
}
```

```
import requests

url = "https://gateway.pixazo.ai/lyria-3/v1/lyria-3/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A calm acoustic folk song with gentle guitar and soft strings. Instrumental only."
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
```

```
const url = 'https://gateway.pixazo.ai/lyria-3/v1/lyria-3/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'A calm acoustic folk song with gentle guitar and soft strings. Instrumental only.'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
```

```
curl -X POST "https://gateway.pixazo.ai/lyria-3/v1/lyria-3/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A calm acoustic folk song with gentle guitar and soft strings. Instrumental only."
  }'
```

## Output

```
{
  "request_id": "lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

[Try Now](https://api.pixazo.ai/api-details#api=lyria-3&operation=music-request)

## Webhook (Optional)

Add the `X-Webhook-URL` header to your submit request to receive a `POST` callback when the job completes — no polling required.

### Webhook Headers

Header

Required

Default

Description

`X-Webhook-URL`

Yes (to enable)

—

HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).

`X-Webhook-Mode`

No

`terminal`

`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at **15s** for tighter progress updates.

### Example: enable webhook

```
X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal
```

### Callback Payload

Your endpoint receives a `POST application/json` with the same shape as the `GET /v2/requests/status/{request_id}` response. Example terminal callback (mode `terminal`):

```
{
  "request_id": "lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "lyria-3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mpeg"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}
```

### Failure callback shape

```
{
  "request_id": "lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lyria-3",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}
```

### Delivery semantics

-   **terminal mode (default)** — exactly one `POST` when the request reaches a terminal status. No callback during `PROCESSING`.
-   **sync mode** — `POST` on every status poll (with delay capped at ~15s) plus a final `POST` at terminal status. Use when you want progress updates.
-   **Idempotency** — use `request_id` as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
-   **Response** — respond `200 OK` within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
-   **HTTPS required** — plain `http://` URLs are rejected.

## Request Parameters - Text to Music

Parameter

Required

Type

Default

Allowed values / range

Description

`prompt`

Yes

string

—

non-empty text

Text prompt describing the song to generate. Include genre, instruments, mood, tempo, lyrics, and structure tags like `[Verse]`, `[Chorus]`, `[Bridge]`. Use timestamps like `[0:00 - 0:30]` to control timing.

`images`

No

array

—

up to 10 image URLs

Input images to inspire the music composition. Array of publicly-reachable URL strings.

## Example Request

```
{
  "prompt": "[Verse 1]\nWalking through the neon glow,\ncity lights reflect below,\nevery shadow tells a story,\nevery corner, fading glory.\n\n[Chorus]\nWe are the echoes in the night,\nburning brighter than the light,\nhold on tight, don't let me go,\nwe are the echoes down below.\n\n[Verse 2]\nFootsteps lost on empty streets,\nrhythms sync to heartbeats,\nwhispers carried by the breeze,\ndancing through the autumn leaves.\n\nGenre: Dreamy indie pop. Mood: Nostalgic and uplifting. Tempo: 110 BPM.",
  "images": [
    "https://example.com/sunset-beach.jpg",
    "https://example.com/forest-path.jpg"
  ]
}
```

## Response

```
{
  "request_id": "lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

## Request Headers

Header

Value

Content-Type

application/json

Cache-Control

no-cache

Ocp-Apim-Subscription-Key

YOUR\_SUBSCRIPTION\_KEY

## Response Handling

Common status codes.

Code

Meaning

202

Accepted — Request queued

400

Bad Request

401

Unauthorized

402

Insufficient Balance

403

Forbidden

429

Too Many Requests

500

Internal Server Error

## Error Responses

Queue system errors and model validation errors.

### Queue System Errors

```
// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance. Required: $0.08"
}
```

```
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'lyria-3' not found or is disabled"
}
```

### Error via Status/Webhook

```
{
  "request_id": "lyria-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lyria-3",
  "error": "Description of the error",
  "output": null
}
```

## Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

### Endpoint

```
GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY
```

## cURL Example

```
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/lyria-3_019d5721-c333-7002-426f-b50cf48bab672"
```

## Response (Completed)

```
{
  "request_id": "lyria-3_019d5721-c333-7002-426f-b50cf48bab672",
  "status": "COMPLETED",
  "model_id": "lyria-3",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lyria-3_019d5721-c333-7002-426f-b50cf48bab672/output.mpeg"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-04-04T06:15:23.699Z",
  "updated_at": "2026-04-04T06:16:20.000Z",
  "completed_at": "2026-04-04T06:16:20.000Z"
}
```

## Response Fields

Field

Type

Description

request\_id

string

Unique request identifier

status

string

QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR

model\_id

string

Model that processed the request

error

string|null

Error message if failed

output.media\_url

array

URLs to generated media (R2 CDN)

output.media\_type

string

MIME type (audio/mpeg)

created\_at

string

When request was created

completed\_at

string|null

When request completed

polling\_url

string

Status URL (initial response only)

## Status Values

Status

Description

QUEUED

Request accepted, waiting to be processed

PROCESSING

Being processed by the model

COMPLETED

Done — output contains the result

FAILED

Failed — check error field

ERROR

System error — not charged

## Status Flow

```
QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR
```

## Typical Workflow

1.  **Send a generate request** to the API endpoint
2.  **Save the `request_id`** from the response
3.  **Poll** every 5-10 seconds: `GET /v2/requests/status/{request_id}`
4.  **When `status` is `"COMPLETED"`**, download from `output.media_url`

**Tip:** Use `X-Webhook-URL` header to get a callback instead of polling.

## Lyria 3 Pro

### Text to Music

## Base URL

```
https://gateway.pixazo.ai/lyria-3-pro/v1
```

## Authentication

All requests require an API key passed via header.

Header

Type

Required

Description

Ocp-Apim-Subscription-Key

string

Yes

Your API subscription key

## Music generate request - Lyria 3 Pro API

## Request Code

HTTP Python JavaScript cURL

```
POST https://gateway.pixazo.ai/lyria-3-pro/v1/lyria-3-pro/generate
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "A calm acoustic folk song with gentle guitar and soft strings. Instrumental only."
}
```

```
import requests

url = "https://gateway.pixazo.ai/lyria-3-pro/v1/lyria-3-pro/generate"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "A calm acoustic folk song with gentle guitar and soft strings. Instrumental only."
}

response = requests.post(url, json=data, headers=headers)
print(response.json())
```

```
const url = 'https://gateway.pixazo.ai/lyria-3-pro/v1/lyria-3-pro/generate';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  prompt: 'A calm acoustic folk song with gentle guitar and soft strings. Instrumental only.'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));
```

```
curl -X POST "https://gateway.pixazo.ai/lyria-3-pro/v1/lyria-3-pro/generate" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  --data-raw '{
    "prompt": "A calm acoustic folk song with gentle guitar and soft strings. Instrumental only."
  }'
```

## Output

```
{
  "request_id": "lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

[Try Now](https://api.pixazo.ai/api-details#api=lyria-3-pro&operation=music-request)

## Webhook (Optional)

Add the `X-Webhook-URL` header to your submit request to receive a `POST` callback when the job completes — no polling required.

### Webhook Headers

Header

Required

Default

Description

`X-Webhook-URL`

Yes (to enable)

—

HTTPS endpoint on your server that will receive the `POST` callback. Must respond `2xx` within a few seconds (process async if needed).

`X-Webhook-Mode`

No

`terminal`

`terminal` — fires once at the final status (`COMPLETED`/`FAILED`/`ERROR`). `sync` — fires on every poll cycle plus the terminal event, and caps the queue’s polling delay at **15s** for tighter progress updates.

### Example: enable webhook

```
X-Webhook-URL: https://your-server.com/webhook/callback
X-Webhook-Mode: terminal
```

### Callback Payload

Your endpoint receives a `POST application/json` with the same shape as the `GET /v2/requests/status/{request_id}` response. Example terminal callback (mode `terminal`):

```
{
  "request_id": "lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "lyria-3-pro",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mpeg"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-05-22T13:17:32.110Z",
  "updated_at": "2026-05-22 13:19:23",
  "completed_at": "2026-05-22 13:19:23"
}
```

### Failure callback shape

```
{
  "request_id": "lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lyria-3-pro",
  "error": "Description of the error",
  "output": null,
  "created_at": "...",
  "updated_at": "...",
  "completed_at": "..."
}
```

### Delivery semantics

-   **terminal mode (default)** — exactly one `POST` when the request reaches a terminal status. No callback during `PROCESSING`.
-   **sync mode** — `POST` on every status poll (with delay capped at ~15s) plus a final `POST` at terminal status. Use when you want progress updates.
-   **Idempotency** — use `request_id` as your idempotency key. Network retries can deliver the same callback more than once; your handler must tolerate duplicates.
-   **Response** — respond `200 OK` within a few seconds. The queue does not block on slow handlers, but persistent failures may stop further deliveries.
-   **HTTPS required** — plain `http://` URLs are rejected.

## Request Parameters - Music generate request

Parameter

Required

Type

Default

Allowed values / range

Description

prompt

Yes

string

—

—

Text prompt describing the song to generate. Include details like genre, instruments, mood, tempo, lyrics, and song structure (e.g. \[Verse\], \[Chorus\], \[Bridge\]). Use timestamps like \[0:00 - 0:30\] to control timing.

images

No

array

—

—

Input images to inspire the music composition (up to 10 images). Array of URL strings.

## Example Request

```
{
  "prompt": "[Verse 1]\nWalking through the neon glow,\ncity lights reflect below,\nevery shadow tells a story,\nevery corner, fading glory.\n\n[Chorus]\nWe are the echoes in the night,\nburning brighter than the light,\nhold on tight, don't let me go,\nwe are the echoes down below.\n\n[Verse 2]\nFootsteps lost on empty streets,\nrhythms sync to heartbeats,\nwhispers carried by the breeze,\ndancing through the autumn leaves.\n\nGenre: Dreamy indie pop. Mood: Nostalgic and uplifting. Tempo: 110 BPM.",
  "images": [
    "https://example.com/sunset-beach.jpg",
    "https://example.com/forest-path.jpg"
  ]
}
```

## Response

```
{
  "request_id": "lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

## Request Headers

Header

Value

Content-Type

application/json

Cache-Control

no-cache

Ocp-Apim-Subscription-Key

YOUR\_SUBSCRIPTION\_KEY

## Response Handling

Common status codes.

Code

Meaning

202

Accepted — Request queued

400

Bad Request

401

Unauthorized

402

Insufficient Balance

403

Forbidden

429

Too Many Requests

500

Internal Server Error

## Error Responses

Queue system errors and model validation errors.

### Queue System Errors

```
// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance. Required: $0.08"
}
```

```
// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'lyria-3-pro' not found or is disabled"
}
```

### Error via Status/Webhook

```
{
  "request_id": "lyria-3-pro_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "lyria-3-pro",
  "error": "Description of the error",
  "output": null
}
```

## Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

### Endpoint

```
GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY
```

## cURL Example

```
curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/lyria-3-pro_019d5721-c333-7002-426f-b50cf48bab672"
```

## Response (Completed)

```
{
  "request_id": "lyria-3-pro_019d5721-c333-7002-426f-b50cf48bab672",
  "status": "COMPLETED",
  "model_id": "lyria-3-pro",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/lyria-3-pro_019d5721-c333-7002-426f-b50cf48bab672/output.mpeg"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-04-04T06:15:23.699Z",
  "updated_at": "2026-04-04T06:16:20.000Z",
  "completed_at": "2026-04-04T06:16:20.000Z"
}
```

## Response Fields

Field

Type

Description

request\_id

string

Unique request identifier

status

string

QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR

model\_id

string

Model that processed the request

error

string|null

Error message if failed

output.media\_url

array

URLs to generated media (R2 CDN)

output.media\_type

string

MIME type (audio/mpeg)

created\_at

string

When request was created

completed\_at

string|null

When request completed

polling\_url

string

Status URL (initial response only)

## Status Values

Status

Description

QUEUED

Request accepted, waiting to be processed

PROCESSING

Being processed by the model

COMPLETED

Done — output contains the result

FAILED

Failed — check error field

ERROR

System error — not charged

## Status Flow

```
QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR
```

## Typical Workflow

1.  **Send a generate request** to the API endpoint
2.  **Save the `request_id`** from the response
3.  **Poll** every 5-10 seconds: `GET /v2/requests/status/{request_id}`
4.  **When `status` is `"COMPLETED"`**, download from `output.media_url`

**Tip:** Use `X-Webhook-URL` header to get a callback instead of polling.
