documentation

image, video, and audio

Generate production media with dedicated Brok models.
image generation

POST /v1/images/generations

curl https://api.brok.fyi/v1/images/generations \
  -H "Authorization: Bearer $BROK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"brok-image-1","prompt":"editorial product photo","n":1,"response_format":"url"}'

Use aspect_ratio or an OpenAI-style size. Set response_format to url or b64_json.

video generation

create, then poll

  • POST/v1/videosReturns 202 with a queued video ID
  • GET/v1/videos/{id}Returns processing, completed, or failed
curl https://api.brok.fyi/v1/videos \
  -H "Authorization: Bearer $BROK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"brok-video-3","prompt":"a calm ocean at sunrise"}'
speech and music

generate audio

  • POST/v1/audio/speechText to speech with brok-speech-2
  • POST/v1/music/generationsMusic generation with brok-music-3

Speech accepts input, voice, speed, volume, pitch, language, and response_format. It returns audio bytes when binary audio is available.