Google Veo3 Fast API Documentation

Google Veo3 Fast API Documentation

Playground

Try it on WaveSpeedAI!

Google Veo 3 Fast creates text-to-video with synchronized audio, delivering faster, more cost-effective results than standard Veo 3; commercial use allowed and pricing starts at $0.25/second. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Veo 3 Fast is a high-speed, cost-efficient version of Google’s Veo 3 model, built for creators who need cinematic results with synchronized audio in record time. It produces realistic 8-second clips featuring dialogue, sound effects, and background music—all natively generated.


Why it looks great

  • Lightning-Fast Generation ⚡ Produces 8-second cinematic videos up to 30% faster than standard Veo 3.

  • Budget-Friendly Efficiency 💰 Up to 80% cost savings, allowing 5× more videos per budget unit.

  • Cinematic Realism 🎬 Generates coherent motion, expressive characters, and balanced lighting for film-like quality.

  • Native Audio Sync 🔊 Automatically includes ambient sounds, speech, and music perfectly matched to on-screen action.

  • Character & Camera Consistency 🎥 Supports reference-based continuity and stable camera direction for precise visual storytelling.


Limits and Performance

  • Max duration per job: 8 seconds
  • Typical generation speed: ~30 seconds per video
  • Resolution: up to 1080p
  • Audio: synchronized voice, SFX, ambience, and background score
  • Size: 16:9 or 9:16

Pricing

Pricing is $0.10 per second without audio or $0.15 per second with audio, for both 720p and 1080p.

DurationWithout AudioWith Audio
4s$0.40$0.60
6s$0.60$0.90
8s$0.80$1.20

Billing Rules

  • Supported durations are 4, 6, and 8 seconds.
  • Total price is the requested duration multiplied by the applicable per-second rate.
  • 720p and 1080p have the same price.
  • generate_audio selects the audio pricing tier.
  • prompt, aspect_ratio, negative_prompt, and seed do not add separate charges.

How to Use

  1. Write a text prompt describing your scene, characters, or story.
  2. Choose duration (up to 8 seconds).
  3. Run generation and preview your result.
  4. Download the MP4 file with synchronized audio.

Pro Tips for Best Results

  • Keep prompts concise but cinematic: specify lighting, motion, and emotion.
  • Use reference images for consistent characters across clips.
  • Combine camera directions (“slow zoom-in,” “tracking shot,” etc.) for dynamic composition.
  • Avoid overly complex multi-scene prompts—stick to one action or setting per clip.
  • If dialogue is critical, use quotation marks in the prompt for clearer speech output.

Notes

  • Actual generation time may vary depending on queue and resolution.
  • Currently optimized for short-form content such as trailers, vlogs, and viral videos.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "16:9",
  "duration": 8,
  "resolution": "720p",
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/google/veo3-fast" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text prompt for generation; Positive text prompt.
aspect_ratiostringNo16:916:9, 9:16Aspect ratio of the video.
durationintegerNo88, 4, 6The duration of the generated media in seconds.
resolutionstringNo720p720p, 1080pVideo resolution.
generate_audiobooleanNotrue-Whether to generate audio.
negative_promptstringNo-Negative prompt for the generation.
seedintegerNo--The random seed to use for the generation.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.