Google Veo3.1 Fast Text To Video API Documentation

Google Veo3.1 Fast Text To Video API Documentation

Playground

Google Veo 3.1 Fast creates text-to-video with native 1080p and synchronized audio, delivering high-quality videos for creators. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Veo 3.1 T2V Fast is the high-speed, cost-optimized version of Google DeepMind’s Veo 3.1 text-to-video model. It converts text prompts into cinematic 1080p videos with natural motion, realistic lighting, and synchronized native audio — all generated up to 30 % faster than the standard model. Perfect for creators who need rapid, high-quality video generation for storytelling, marketing, and short-form content production.

🎬 Why it stands out

• Cinematic Realism Produces high-fidelity motion with natural lighting, accurate perspective, and fluid camera transitions.

• Native Audio Generation Automatically generates synchronized sound—including ambient noise, effects, and light music—perfectly aligned with the visuals.

• Dialogue & Lip-Sync Enables speaking characters or realistic expressions, ideal for storytelling, marketing, and short-form content.

• Consistent Subject & Style Retains the identity,tone of your input prompt throughout the motion sequence.

Pricing

Pricing depends on the requested duration, resolution, and whether audio generation is enabled.

Example Costs

Billing Rules

• Total price is the requested duration multiplied by the applicable per-second rate.
• generate_audio selects the audio pricing tier.
• prompt, aspect_ratio, negative_prompt, and seed do not add separate charges.

🚀 How to Use

2. Write a Prompt Describe the desired motion, mood, and camera movement.

> Example: “Slow cinematic zoom out as wind moves through the trees and sunlight flickers across the leaves.”

3. Adjust Settings Select the video duration and resolution (720p, 1080p, or 4K).

4. Generate the Video Submit your prompt — Veo 3.1 T2V automatically creates motion, lighting, and audio.

5. Preview & Download Review the result, refine the prompt if needed, and download the final MP4.

💡 Pro Tips

• Keep prompts focused on a single subject or action for best stability.
• Add camera directions like “tracking shot,” “slow pan,” or “handheld style” to control movement.
• Specify lighting and mood (e.g., bright daylight, soft sunset glow).
• Avoid conflicting motion requests to maintain smooth results.

📝 Notes

• Actual processing time depends on queue load and resolution.
• Optimized for cinematic shorts, ads, and social media clips.
• Please ensure your prompts comply with Google’s Safety Guidelines — if an error occurs, revise your prompt and try again.

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": "1080p",
  "generate_audio": true
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/google/veo3.1-fast/text-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters