Built by Metorial, the integration platform for agentic AI.
Retrieve available voices from Astica's voice AI platform. Returns the catalog of built-in voices (expressive, programmable, neural) and any custom voice clones associated with your account. Use this to discover available voice identifiers for use with the Text to Speech tool.
Analyze an image using Astica's computer vision AI. Supports image captioning, object detection, face detection, OCR text reading, content moderation, tagging, GPT-powered descriptions, brand detection, celebrity recognition, and landmark detection. Provide an image via HTTPS URL or Base64-encoded string, and select which vision capabilities to apply.
Convert text to natural-sounding speech audio using Astica's voice AI. Choose from 500+ voices across multiple categories including expressive, programmable, neural, and cloned voices. Returns Base64-encoded WAV audio and optionally word-level timestamps for precise playback synchronization.
Transcribe audio to text using Astica's hearing AI. Converts spoken words from audio files into written text with high accuracy and multilingual support. Accepts audio via HTTPS URL or Base64-encoded string in WAV or MP3 format.
Generate text using Astica's GPT-S natural language processing engine. Produces human-like text, answers questions, creates stories, and generates diverse content based on prompts. Supports configurable temperature, token limits, and optional system instructions for controlling output behavior.
Generate AI images from text prompts using Astica's image generation API. Creates realistic photographs and creative images at 1024x1024 resolution. Supports quality settings, negative prompts to exclude unwanted elements, reproducible generation via seed values, and content moderation filtering.