astica

Developer toolsAPI key

Describe, tag, read and moderate images with asticaVision, turn text into speech with asticaVoice, and generate text with astica GPT-S.

6 actions

Action	Effect	Data handled
astica_ai_describe_imageAnalyzes an image from an https URL or base64 data: captions, a long GPT description, tags, objects, text (OCR), faces, brands, landmarks, colors or moderation scores	read	Personal data
astica_ai_text_to_speechSpeaks text with an expressive, programmable, neural or cloned voice and returns WAV audio as base64, optionally with word timestamps	write	Personal data
astica_ai_get_speech_taskReturns the status of a low priority speech job, and its base64 WAV audio when done	read	Personal data
astica_ai_list_voicesLists the public voices available for text to speech	read	General
astica_ai_list_voice_clonesLists the account's private custom voice clones and whether each is ready	read	General
astica_ai_generate_textGenerates text from a prompt with the astica GPT-S language model, which astica offers for research use	write	Personal data

Sign-in

Also included

dexby.createSession({
  userId: customer.id,
  connectors: ['astica_ai']
})