NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Astica AI connects to a Nagent workspace with an API key. Once it is connected, agents can call 2 Astica AI actions: "Analyze Audio" and "ASTICA_READ_TEXT". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Astica AI, with input parameters and output schema.
ASTICA_AI_ANALYZE_AUDIOTool to analyze audio input for transcription. Use when you need to convert an audio URL or Base64 string to text.
Input parameters
Set to 0 for complete transcription at once, 1 for streaming partial results as they become available
HTTPS URL to .wav/.mp3 audio file or Base64-encoded audio string
Set to 0 for standard processing priority, 1 for low-priority processing which may be slower but reduces API costs
Speech-to-text model version. Use '1.0_full' for standard or '2.0_full' for advanced transcription
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ASTICA_AI_ASTICA_READ_TEXTPerform OCR (Optical Character Recognition) on an image to extract text. Supports HTTPS image URLs and Base64-encoded images. Returns detected text blocks with bounding box coordinates. Works with printed text, handwritten notes, and various image qualities. Note: SVG and WebP formats are not supported.
Input parameters
HTTPS URL of the image to analyze (JPG, PNG, GIF, BMP supported) or Base64-encoded image string.
AsticaVision model version. '2.0_full' is stable and recommended. '2.1_full' offers additional features but may have compatibility issues with some images.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 2 Astica AI actions on Nagent: "Analyze Audio" and "ASTICA_READ_TEXT". Analyze Audio: Analyze audio input for transcription. Each action is listed on this page with its input parameters and its output.
Astica AI connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Analyze Audio takes 1 required input: audio_input. It also takes 3 optional inputs: do_stream, low_priority and model_version. It returns data, error and successful.