Openai Whisper With Video API Documentation

Openai Whisper With Video API Documentation

Playground

OpenAI Whisper Large v3 (Video-to-Text) delivers high-accuracy multilingual transcription directly from video files, with automatic language detection and optional timestamped, subtitle-ready segments. Built for stable production use with a ready-to-use REST API, fast response, no cold starts, and predictable pricing.

Features

OpenAI Whisper — Video-to-Text is a production-ready speech recognition endpoint powered by Whisper large-v3. It transcribes or translates speech directly from video files by extracting audio and returning clean, readable text, with optional word-level timestamps for subtitle and alignment workflows.

Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pay-per-second pricing.

Key capabilities

• Video input support (audio is extracted automatically)
• Two tasks: transcribe and translate
• Language selection: auto detection or manual language code
• Optional word-level timestamps via enable_timestamps
• Optional sync response via enable_sync_mode (API only)

Parameters

How to use

1. Upload video (or paste a public video URL).
2. Set language:

• Use auto for most cases.
• Choose a specific language code if detection is unstable.

3. Choose task:

• transcribe for same-language transcription
• translate for translated output

4. (Optional) Enable enable_timestamps if you need subtitle timing/alignment.
5. (Optional) Add a prompt to guide formatting or terminology (names, jargon, punctuation).
6. Run and read the transcript output.

API note: enable_sync_mode is not shown as a normal UI option; it’s only available through the API.

Pricing

Examples

Notes

• If you use a URL, it must be publicly accessible; the UI showing a preview thumbnail is a good sanity check.
• Timestamps are best for subtitles and editing, but may take longer to process.
• For best accuracy, use clear speech and minimize background music/noise.

More Models to Try

• OpenAI Whisper Turbo on WaveSpeedAI — Faster, cost-efficient speech-to-text for real-time or high-volume transcription pipelines while keeping strong multilingual recognition quality.

Duration limit

The maximum supported video duration is 10 minutes. Longer video is automatically trimmed to 10 minutes before processing.

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'
{
  "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
  "language": "auto",
  "task": "transcribe",
  "enable_timestamps": false
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/openai-whisper-with-video" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters