Getting Started API Documentation
The cognitive API was intended to make it easy for developers to integrate different artificial intelligence into their applications without having to deploy models or maintain the necesary infrastructure. You can find API documentation and code samples for each type of cognitive intelligence available through the API.
- Each API is limited to 45 requests per minute allowing a total of 90 requests per minute when using both Vision and Voice.
- Model Training and Custom Model API both have an increased default limit of 90 requests per minute.
- If an increased limit is required, please submit a ticket and describe the use case.
asticaVoice: Detailed Computer Vision
Capable of multiple computer visions tasks including facial recogntion, object detection and vision assistance. It is capable of providing detailed descriptives for each photo analyzed.
asticaListen: Speech to Text Hearing AI
Convert conversations into text in real-time or provide an audio file input to be transcribed. asticaListen offers accurate transcription even in noisy environments.
asticaVoice: Realistic Voice AI
Interact with users through voice. Capable of 40+ different realistic voices, asticaVoice allows you to choose an age, gender, and nationality that is most suitable for your users.
GPT-S: Natural Language Processing
Offering unfiltered output, GPT-S is a natural language processing engine trained on long-form content generation. Automatically summarize text, write blog posts, or engage with users.
In the coming weeks, the developer API will be expanded to include additional models and capabilities. Write a message for earlier access to private models and documentation listed on the dashboard.
Discover More AI
Experiment with different kinds of artificial intelligence. See, hear, and speak with astica.