Skip to main content
POST
https://gptproto.com
/
api
/
v3
/
google
/
veo3
/
text-to-video
veo3 (Text To Video)
curl --request POST \
  --url https://gptproto.com/api/v3/google/veo3/text-to-video

​
Authentication

  1. Sign up for a GPTProto account at https://gptproto.com
  2. Navigate to the API Keys section in your dashboard
  3. Generate a new API key (sk-xxxxx)
  4. Copy and securely store your API key For authentication details, please refer to the Authentication section.

​
Initiate Request

curl --location 'https://gptproto.com/api/v3/google/veo3/text-to-video' \
--header 'Authorization: GPTPROTO_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
  "prompt": "A young woman walks alone under a transparent umbrella in a quiet alley during light rain, soft city lights reflecting on the wet pavement. Her pace is calm and thoughtful. The camera follows slowly behind her, occasional droplets hitting the lens. Subtle piano music plays, evoking a melancholic but peaceful mood. Dreamy, cinematic, slightly slow motion.",
  "aspect_ratio": "16:9",
  "enhance_prompt": true
}'

​
Query Result

If the request that generated your content includes the parameter enable_sync_mode set to true (some models do not support this parameter, but you still need to query the result by id), you must call the Query Result endpoint to retrieve the final output. 
curl -X GET "https://gptproto.com/api/v3/predictions/{id}/result" \
  -H "Authorization: GPTPROTO_API_KEY" \
  -H "Content-Type: application/json"
After submitting your prediction request, the response will contain the id you need.
You can find it in either:
  • data.id – the unique identifier of the prediction
  • data.urls[0].get – a ready-to-use GET URL that already embeds the id
{
    "data": {
        "id": "abc",
        "model": "model_name",
        "outputs": [],
        "urls": {
            "get": "https://gptproto.com/api/v3/predictions/abc/result"
        },
        "status": "completed",
        "error": null,
        "executionTime": 0,
        "timings": {
            "inference": 0
        },
        "has_nsfw_contents": [],
        "created_at": "2026-01-01 00:00:00"
    },
    "message": "success",
    "code": 200
}

​
Parameters

​
Path Parameters

Endpoint: https://gptproto.com/api/v3/google/{model}/{scene}
Body parameters may vary depending on the scene. Incorrect scene selection may cause parameters to fail. Please choose the appropriate scene based on your actual needs.
sceneexampleAvailable Models
text-to-videohttps://gptproto.com/api/v3/google/{model}/text-to-videoAll models
image-to-videohttps://gptproto.com/api/v3/google/{model}/image-to-videoAll models
reference-to-videohttps://gptproto.com/api/v3/google/{model}/reference-to-videoveo3 veo3-fast veo3.1 veo3.1-fast (not supported by pro models)

​
Core Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstring✅ Yes--A text description of the desired video. Supports audio cues for Veo 3 and later.
imagestring❌ No--Source image URL for image-to-video generation.
imagesarray❌ No-1~3 itemsArray of reference image URLs for reference-to-video generation. Not supported by pro models.
last_imagestring❌ No--The last frame image URL for interpolation video generation. Must be used in combination with the image parameter.
aspect_ratiostring❌ No16:916:9
9:16		The aspect ratio of the generated video.

​
Advanced Parameters

ParameterTypeRequiredDefaultRangeDescription
enhance_promptboolean❌ Notruetrue, falseWhether to enhance the prompt for better video quality.
enable_upsampleboolean❌ No-true, falseWhether to enable upsampling for higher resolution output.
resolutionstring❌ No720p720p
1080p
4k		The resolution of the generated video. 1080p and 4k only support 8s duration.

​
Model Comparison

FeatureVeo 3.1 / Veo 3.1 FastVeo 3.1 ProVeo 3 / Veo 3 FastVeo 3 Pro
text-to-video✅✅✅✅
image-to-video✅✅✅✅
reference-to-video✅❌✅❌
Audio cues in prompt✅✅✅✅
Resolution720p, 1080p, 4k720p, 1080p, 4k720p, 1080p, 4k720p, 1080p, 4k
Aspect ratios16:9, 9:1616:9, 9:1616:9, 9:1616:9, 9:16
Notes:
  • Fast models (veo3-fast, veo3.1-fast): Optimized for speed with lower latency, suitable for high-volume generation tasks.
  • Pro models (veo3-pro, veo3.1-pro): Higher quality output with enhanced detail and coherence. Does not support reference-to-video.
  • 1080p / 4k resolution: Only available with 8-second duration.
  • Video retention: Generated videos are stored on the server for 2 days, after which they are removed.
  • Watermarking: Videos are watermarked using Google SynthID.

​
Error Codes

​
Common Error Codes

Error CodeError NameDescription
401UnauthorizedAPI key is missing or invalid
403ForbiddenYour API key doesn’t have permission to access this resource, or insufficient balance for the requested operation
429Too Many RequestsYou’ve exceeded your rate limit
500Internal server errorAn internal server error occurred
503Content policy violationContent blocked due to safety concerns (actual status code is 400)