VEED Lipsync 2.0 API, VEED Fabric 1.0 API, Veed API: Pricing, Documentation

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state. Provide a Webhook URL via header on the submit request.

Example: enable Webhook

curl -X POST 'https://gateway.pixazo.ai/veed-clean-audio/v1/clean-audio' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/transcribe-sample.wav", "output_format": "flac", "target_lufs": -19, "strength": 0.874}'

Callback Payload (success)

{
  "request_id": "veed-clean-audio_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-clean-audio",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.flac"
    ],
    "media_type": "audio/flac"
  },
  "created_at": "2026-10-06T16:09:09.763Z",
  "completed_at": "2026-10-06 16:10:18"
}

Failure callback shape

{
  "request_id": "veed-clean-audio_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "veed-clean-audio",
  "error": "Description of the failure"
}

Delivery semantics

• terminal mode: one Webhook callback when the request is COMPLETED or ERROR.
• sync mode: a Webhook callback on every poll while the request is processing (status PROCESSING), plus the final COMPLETED/ERROR callback.
• Callbacks are idempotent on request_id — de-duplicate on it.
• Respond 200 within a few seconds; the Webhook endpoint must be HTTPS.

Request Parameters

Good to know

• Each request cleans one recording. batch_size, num_images, number_of_images, n, count are rejected — send one request per file.
• Send the file as audio_url only; audio_urls and video_url are rejected. For a video, send its URL as audio_url: the audio track is cleaned and returned as an audio file.
• There is no length field: duration, seconds, num_frames, frames_per_second, music_length_ms are rejected. The billed length is measured from the file.
• The model takes no prompt. Send every field at the top level of the JSON body; parameters, content, text are rejected.
• Values are case-sensitive: use flac, not FLAC.
• When you leave a field out, the defaults apply: flac, a loudness target of −19 LUFS and a strength of 0.874.
• Only target_lufs accepts null. Omit the other optional fields you do not use — do not send them as null.
• There is no seed parameter.
• Webhooks are set with the X-Webhook-URL / X-Webhook-Mode headers; webhook_url and webhook_mode in the JSON body are rejected.

Input Audio

• Send exactly one file in audio_url: a publicly reachable https URL that serves the file itself (no redirects), or a data URI such as data:audio/wav;base64,.... Use a URL for anything large: a data URI over 50 MB is refused. A list of files is rejected.
• Any audio or video format ffmpeg can decode works — for example WAV, MP3, M4A, AAC, OGG, FLAC, MP4, MOV or WebM. For a video, its audio track is cleaned and returned as an audio file; the video itself is not returned.
• Multi-channel audio is mixed down to mono.
• Up to 30 minutes and 512 MB per file. A longer recording whose file states its length is refused when you submit; split it into shorter segments.
• The link is checked when you submit: a URL that cannot be downloaded, or that returns a web page or an empty file instead of a recording, is refused at once with a 400 and its hold is released. Large files are fetched when processing starts, so keep the link valid until the request completes.

Example: send the recording as a data URI

{
  "audio_url": "data:audio/wav;base64,UklGRiQAAABXQVZFZm10IBAAAAABAAEA...",
  "output_format": "wav"
}

Output Audio

The cleaned recording is 48 kHz, mono, 16-bit, and the same length as the input, give or take a fraction of a second. Background noise is removed from the speech, and the loudness is normalized — aimed at target_lufs, within a true-peak cap (see Loudness below) — unless you send null.

Loudness

The default target is −19 LUFS integrated, and the true peak is capped at −1.1 dBTP. When the cap is reached first, the output comes out quieter than the target. To keep the original level and skip loudness normalization, send "target_lufs": null:

{
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/transcribe-sample.wav",
  "output_format": "wav",
  "target_lufs": null
}

Strength

strength sets how much of the background stays under the voice: at the default 0.874 the noise floor is held about 18 dB down. Lower it to keep more of the room's sound behind the speaker.

Request Headers

Response Handling

Parameter problems are caught when you submit and returned as a 400, before any hold is placed on your balance. A recording that cannot be downloaded is also refused at submit with a 400, and its hold is released at once. Problems that need the model to run are reported through the status endpoint as status: "ERROR", with a message in error saying what went wrong. Failed requests are not billed — the hold is released in full.

Missing audio_url (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'audio_url' is required",
  "violations": [
    "'audio_url' is required"
  ]
}

A value that is not allowed (synchronous 400)

{
  "error": "Invalid request parameters",
  "message": "'output_format' must be one of: \"flac\", \"wav\" (got \"FLAC\")",
  "violations": [
    "'output_format' must be one of: \"flac\", \"wav\" (got \"FLAC\")"
  ]
}

A recording longer than 30 minutes (synchronous 400, no hold)

{
  "error": "Input too long",
  "message": "The source media is 2400s. This API accepts inputs up to 1800s — split it into shorter segments.",
  "max_input_seconds": 1800,
  "input_seconds": 2400
}

A file that cannot be downloaded (synchronous 400, hold released)

{
  "request_id": "veed-clean-audio_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "error": "Asset proxy failed",
  "message": "Failed to proxy asset https://example.com/recording.wav: 404 Not Found",
  "failures": [
    {
      "url": "https://example.com/recording.wav",
      "error": "404 Not Found"
    }
  ]
}

Retrieving Results

Poll the status endpoint with the request_id from the submit response until status is COMPLETED or ERROR, then download the audio from output.media_url. Treat any status other than QUEUED, PROCESSING or COMPLETED as a failure. Longer recordings take longer to process.

Endpoint

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

cURL example

curl 'https://gateway.pixazo.ai/v2/requests/status/veed-clean-audio_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "veed-clean-audio_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-clean-audio",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.flac"
    ],
    "media_type": "audio/flac"
  },
  "created_at": "2026-10-06T16:09:09.763Z",
  "completed_at": "2026-10-06 16:10:18"
}

Response Fields

Status Values & Flow

QUEUED → PROCESSING → COMPLETED (success) or ERROR (failure).

Typical workflow

1. Send the request to POST https://gateway.pixazo.ai/veed-clean-audio/v1/clean-audio.
2. Save the request_id from the 202 response.
3. Poll GET /v2/requests/status/{request_id} every 10 seconds or so, or use a Webhook instead.
4. When status is COMPLETED, download the audio from output.media_url.

How billing is measured

Billing is measured per minute of input audio: the length of the recording you send, rounded to whole seconds and then up to the next full minute, with a one-minute minimum — a 4-minute 10-second file is billed as 5 minutes, a 20-second file as 1 minute. For a video file, the length of its audio track is billed. output_format, target_lufs and strength do not change the amount.

When you submit, a hold is placed on your balance: for the file's length when the file states it (WAV, FLAC, MP4, MOV, M4A, and MP3 with a length header), otherwise for the 30-minute maximum. When the request completes, the charge is settled to the measured length and the rest of the hold is released. A failed request is not billed — its hold is released in full.

The current rate is shown in the pricing panel on this page.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive a callback when the request reaches a terminal state. Pass the webhook headers on the submit request; the gateway will POST the result to your URL.

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/veed-lipsync-v2/v1/video-to-video/lip-sync" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  -H "X-Webhook-URL: https://your-server.com/webhooks/pixazo" \
  -H "X-Webhook-Mode: terminal" \
  --data-raw '{ "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/lipsync/talking-head-17s.mp4", "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/test-audio/hg_audio17.mp3" }'

Callback Payload (success)

{
  "request_id": "veed-lipsync-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-lipsync-v2",
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-lipsync-v2_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  }
}

Failure callback shape

{
  "request_id": "veed-lipsync-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "error": "Failed to download the file. Please check if the URL is accessible."
}

• terminal mode delivers one callback on COMPLETED or ERROR; sync mode delivers on each status transition.
• Deliveries are keyed by request_id — make your handler idempotent.
• Respond with HTTP 200 within a few seconds; non-2xx responses are retried.
• The webhook URL must be HTTPS and publicly reachable.

Request Parameters

Content Item Types & Limits

Request Headers

Response Handling

Common status codes returned by the submit endpoint.

Error Responses

Queue-system errors are returned at submit time; generation errors are surfaced via the status endpoint / webhook with status: "ERROR".

// 402 — insufficient balance
{ "error": "Insufficient balance", "message": "Wallet balance is too low for this request." }

// 400 — model not found / invalid body
{ "error": "Model not found", "message": "Model 'veed-lipsync-v2' not found or is disabled" }

// generation failure (via status / webhook)
{ "request_id": "veed-lipsync-v2_019dxxxx...", "status": "ERROR", "error": "Failed to download the input file." }

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 -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/veed-lipsync-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "veed-lipsync-v2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-lipsync-v2",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-lipsync-v2_019dxxxx-xxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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

Status Values & Flow

Typical workflow

QUEUED → PROCESSING → COMPLETED (or FAILED / ERROR). Submit the request, then poll GET /v2/requests/status/{request_id} (or use a webhook) until the status is terminal, then download the video from output.media_url.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

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

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

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": "veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-fabric-1-0-api-130",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.png"
    ],
    "media_type": "image/png"
  },
  "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": "veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "veed-fabric-1-0-api-130",
  "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 - VEED Fabric 1.0 API generate request

Content Item Types & Limits

Response

{
  "request_id": "veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "/v2/requests/status/veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Response Handling

Common status codes for VEED Fabric 1.0 API generate request.

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 'veed-fabric-1-0-api-130' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "veed-fabric-1-0-api-130",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

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

Endpoint

GET /v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "/v2/requests/status/veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "veed-fabric-1-0-api-130_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-fabric-1-0-api-130",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-fabric-1-0-api-130_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

Status Values

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.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

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

Using curl? These are HTTP request headers — pass each with -H, e.g. -H "X-Webhook-URL: https://your-server.com/webhook/callback". Do not paste them as bare lines, and end every line of a multi-line command with \.

Webhook Headers

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": "veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-video-background-remover-541",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx/output.mp4"
    ],
    "media_type": "video/mp4"
  },
  "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": "veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "veed-video-background-remover-541",
  "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 - Veed Video Background Remover generate request

Content Item Types & Limits

Response

{
  "request_id": "veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Response Handling

Common status codes for Veed Video Background Remover generate request.

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 'veed-video-background-remover-541' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "veed-video-background-remover-541",
  "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 -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

{
  "request_id": "veed-video-background-remover-541_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-video-background-remover-541",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-video-background-remover-541_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

Status Values

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.

Authentication

All requests require an API key passed via header.

Webhook (Optional)

Instead of polling, you can receive a callback when the request reaches a terminal state. Pass the webhook headers on the submit request; the gateway will POST the result to your URL.

Example: enable webhook

curl -X POST "https://gateway.pixazo.ai/veed-lipsync/v1/video-to-video/lip-sync" \
  -H "Content-Type: application/json" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
  -H "X-Webhook-URL: https://your-server.com/webhooks/pixazo" \
  -H "X-Webhook-Mode: terminal" \
  --data-raw '{ "video_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/lipsync/talking-head-17s.mp4", "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/test-audio/hg_audio17.mp3" }'

Callback Payload (success)

{
  "request_id": "veed-lipsync_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-lipsync",
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-lipsync_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  }
}

Failure callback shape

{
  "request_id": "veed-lipsync_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "error": "Failed to download the file. Please check if the URL is accessible."
}

• terminal mode delivers one callback on COMPLETED or ERROR; sync mode delivers on each status transition.
• Deliveries are keyed by request_id — make your handler idempotent.
• Respond with HTTP 200 within a few seconds; non-2xx responses are retried.
• The webhook URL must be HTTPS and publicly reachable.

Request Parameters

Content Item Types & Limits

Request Headers

Response Handling

Common status codes returned by the submit endpoint.

Error Responses

Queue-system errors are returned at submit time; generation errors are surfaced via the status endpoint / webhook with status: "ERROR".

// 402 — insufficient balance
{ "error": "Insufficient balance", "message": "Wallet balance is too low for this request." }

// 400 — model not found / invalid body
{ "error": "Model not found", "message": "Model 'veed-lipsync' not found or is disabled" }

// generation failure (via status / webhook)
{ "request_id": "veed-lipsync_019dxxxx...", "status": "ERROR", "error": "Failed to download the input file." }

Retrieving Results

Poll the status endpoint with the request_id until status is COMPLETED (or FAILED/ERROR).

curl -X GET "https://gateway.pixazo.ai/v2/requests/status/veed-lipsync_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" \
  -H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY"

Completed response

{
  "request_id": "veed-lipsync_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "veed-lipsync",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/veed-lipsync_019dxxxx.../output.mp4"],
    "media_type": "video/mp4"
  },
  "created_at": "2026-06-30T09:20:33.812Z",
  "completed_at": "2026-06-30T09:22:19.000Z"
}

Response Fields

Status Values & Flow

Typical workflow

QUEUED → PROCESSING → COMPLETED (or FAILED / ERROR). Submit the request, then poll GET /v2/requests/status/{request_id} (or use a webhook) until the status is terminal, then download the video from output.media_url.