Use Astica AI from Claude
Add the Astica AI connection to a Space that runs Claude, then use it from every channel in that Space.
ConnectorAstica AI
Astica AI integration for Claude and Codex
Connect Astica AI once, then control which Spaces can use its approved tools and data without pasting credentials into prompts or threads.
CategoryDesign & Media
Use Astica AI from Codex
Add the Astica AI connection to a Space that runs Codex, then use it from every channel in that Space.
Use Astica AI from Sidekick
Connect your own OpenClaw to Sidekick while type.com provides the conversations, permissions, connections, skills, and automations.
Design & Media
What the Astica AI connector can do
Astica AI offers cognitive APIs covering vision, OCR, and speech processing for developers building AI-powered features. In type.com, a content or operations Space can ask Claude to transcribe an audio clip or extract text from a scanned image, turning unstructured media into usable text without manual transcription.
One connection, many Spaces
Connect Astica AI once, then decide which Spaces can use it in threads, skills, automations, and coding work.
What teams do with Astica AI in type.com
Transcribe a recorded call or voice memo
Convert an audio file or URL into text so the content can be searched, summarized, or logged.
Transcribe this customer call recording using Astica AI and summarize the main complaint.
Pull text out of a scanned document
Extract printed or handwritten text from an image so it can be copied into a record instead of retyped.
Run OCR on this scanned invoice image with Astica AI and give me the extracted text.
Digitize handwritten notes from a whiteboard photo
Convert a photo of handwritten notes into text so the content can be shared and searched afterward.
Extract the text from this whiteboard photo using Astica AI's OCR tool.
Representative actions
- Analyze Audio
Converts an audio URL or base64 audio input into a text transcription.
- ASTICA_READ_TEXT
Performs OCR on an image to extract printed or handwritten text with bounding box positions.
Connection
API and auth details
Astica AI provides cognitive APIs for computer vision, image description, object detection, face recognition, image moderation, OCR-like reading, speech-to-text, text-to-speech voices, GPT-S natural language processing, custom vision/model training, JavaScript SDK usage, demos, and rate-limited developer API access.
- Source
- type.com catalog metadata
- Auth schemes
- API key
- API reference
- https://www.astica.org/api-docs/asticaVision/
- Official site
- https://astica.ai/
FAQ
Questions people ask before connecting Astica AI
Can Claude transcribe audio and images with Astica AI?
Yes. With an Astica AI connection shared to your Space, ask Claude in a thread to transcribe audio or extract text from an image, with results posted back to the thread.
How does type.com authenticate with Astica AI?
Astica AI uses an API key. An admin adds it once when setting up the connection and controls which Spaces can run transcription or OCR through it.
What file types work with the Astica AI connection?
The connected actions accept audio URLs or base64 audio for transcription, and HTTPS image URLs or base64 images for OCR. Check vendor documentation for specific format support.
Is this the same as an MCP server for Astica AI?
Not exactly. type.com uses connectors and connections to give selected Spaces access to approved app tools and data. Some connectors use hosted MCP, while others use OAuth, API keys, service accounts, or custom APIs.
More design & media connectors
All Design & Media integrationsConnect Supportivekoala to Claude in type.com to render images from templates, manage a template library, and track generated assets in one thread.
Connect Templated to Claude in type.com to clone templates, organize them into folders, and render finished images or PDFs from a thread.
Connect V0 to Claude in type.com to generate chat responses, spin up projects, set environment variables, and organize chats by project.
Connect Vimeo to Claude in type.com to review video metadata, browse team libraries, and pull transcripts from a thread.