# Google Veo 3 (with Audio) Text-to-Video Generation

> Google Veo 3 (with Audio) Text-to-Video Generation is a paid API for AI agents from make-video.withzero.ai, paid per call via MPP, metered — billed by usage, status unknown (last checked 2026-10-09).

Generates a realistic 720p video clip with optional native audio from a text prompt using Google Veo 3, returning a job ID to poll for completion.

## Facts

- Endpoint: POST https://make-video.withzero.ai/veo3?utm_source=zero.xyz
- Price: metered — billed by usage
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-09
- Activations on Zero: 0
- Provider: make-video.withzero.ai
- Website: https://make-video.withzero.ai
- Canonical page: https://www.zero.xyz/c/make-video-withzero-ai-google-veo-3-with-audio-text-to-video-generation-f89e8681
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jDax3ugyCAwVHL3KKtV7k

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 make-video-withzero-ai-google-veo-3-with-audio-text-to-video-generation-f89e8681 -d '<json body>'
```

Example prompt: Generate a realistic 6-second 720p video with native audio of a golden retriever running through autumn leaves in a park — make sure audio is enabled and avoid any blurry or dark scenes.

## When to prefer this

Choose this endpoint when you need Google Veo 3's top-tier photorealism with the option for native synchronized audio, at 720p resolution with 4, 6, or 8-second durations. Prefer this over Veo 3 Fast when quality and realism matter more than speed or cost. Prefer over Kling, Sora, or Seedance when Google's cinematic realism is specifically desired, or when native audio generation in the same render pass is required.

## Known failure modes

- Invalid or missing prompt returns a 400 validation error
- Duration not in allowed set (4/6/8s) is rejected at preCheck
- Audio toggle supplied on unsupported model variant is rejected
- Insufficient USDC balance causes payment failure before job is queued
- fal.ai backend timeout results in delayed or failed job status
- Image URL field provided but ignored (not required for this text-to-video model)
- Job ID polling may return pending status for several minutes before video is ready

## How this service works

Google Veo 3 (with audio) — text-to-video. Per-model alias for POST /run with model="veo3". Google Veo 3 standard — top-tier realism with optional native audio. 720p, durations 4/6/8s. Preview the charge via free GET /price/veo3?duration=…&resolution=…; poll the job via free GET /status/:id (returned job_id).

## Output

Returns a JSON object containing a job_id to poll for video completion, a status_url for polling, the underlying fal.ai model ID, a human-readable model name, the resolved input parameters (duration, resolution, audio flag), a price breakdown in USD, an estimated completion time in seconds, and a recommended polling interval in seconds.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "prompt"
 ],
 "properties": {
  "prompt": {
   "type": "string",
   "maxLength": 2000,
   "minLength": 1,
   "description": "Text description of the video to generate."
  },
  "duration": {
   "type": "integer",
   "minimum": 0,
   "description": "Clip duration in seconds. Per-model allow-list applied at preCheck.",
   "exclusiveMinimum": true
  },
  "image_url": {
   "type": "string",
   "format": "uri",
   "description": "Public http(s) URL of the starting image. Required for image-to-video models (wan, hailuo)."
  },
  "resolution": {
   "type": "string",
   "description": "Output resolution. Per-model allow-list applied at preCheck."
  },
  "aspect_ratio": {
   "type": "string",
   "description": "Output aspect ratio. Per-model allow-list applied at preCheck."
  },
  "generate_audio": {
   "type": "boolean",
   "description": "Generate native audio track. Only accepted by models that have an audio toggle (veo3)."
  },
  "negative_prompt": {
   "type": "string",
   "maxLength": 1000,
   "description": "Optional — describe what to avoid."
  }
 },
 "additionalProperties": false
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "job_id",
  "status_url",
  "endpoint",
  "model",
  "model_name",
  "inputs",
  "price",
  "estimated_seconds",
  "poll_interval_seconds"
 ],
 "properties": {
  "model": {
   "type": "string",
   "description": "Underlying fal.ai model id."
  },
  "price": {
   "type": "object",
   "required": [
    "cost_usd",
    "markup_usd",
    "charge_usd",
    "breakdown"
   ],
   "properties": {
    "cost_usd": {
     "type": "number"
    },
    "breakdown": {
     "type": "string"
    },
    "charge_usd": {
     "type": "number"
    },
    "markup_usd": {
     "type": "number"
    }
   },
   "additionalProperties": false
  },
  "inputs": {
   "type": "object",
   "required": [
    "duration",
    "resolution"
   ],
   "properties": {
    "duration": {
     "type": "number"
    },
    "resolution": {
     "type": "string"
    },
    "generate_audio": {
     "type": "boolean"
    }
   },
   "description": "Echo of resolved inputs (after defaults applied).",
   "additionalProperties": false
  },
  "job_id": {
   "type": "string",
   "description": "Internal id; pass to GET /status/:job_id."
  },
  "endpoint": {
   "type": "string",
   "description": "The model slug that handled this submit."
  },
  "model_name": {
   "type": "string",
   "description": "Human-readable model name."
  },
  "status_url": {
   "type": "string",
   "format": "uri",
   "description": "Full URL to poll for completion."
  },
  "estimated_seconds": {
   "type": "number"
  },
  "poll_interval_seconds": {
   "type": "number"
  }
 },
 "additionalProperties": false
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/make-video-withzero-ai-google-veo-3-with-audio-text-to-video-generation-f89e8681/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from make-video.withzero.ai](https://www.zero.xyz/host/make-video.withzero.ai/llms.txt)