Pricing
Tasks
Retrieve a list of tasks supported by the platform.
GET
Explore the wide range of tasks supported by Bytez. These tasks enable seamless integration with open-source and closed-source AI models.
Task List
Current tasks supported, with a brief description of each.
| Task Name | Description |
|---|---|
| Audio Classification | Classify audio files into predefined categories. |
| Automatic Speech Recognition (ASR) | Convert speech to text with high accuracy. |
| Chat | Facilitate conversational AI capabilities. |
| Depth Estimation | Predict depth information from images. |
| Document Question Answering | Extract answers from documents based on questions. |
| Feature Extraction | Extract features from various types of data (text, audio, images, etc.). |
| Fill Mask | Predict masked tokens in a text sequence. |
| Image Classification | Categorize images into predefined classes. |
| Image Feature Extraction | Extract visual features from images for further processing. |
| Image Segmentation | Partition an image into multiple segments. |
| Image Text-to-Text | Generate text based on the content of images. |
| Image to Text | Generate descriptive text captions for images. |
| Mask Generation | Generate mask images for specific tasks like segmentation. |
| Object Detection | Identify and locate objects within an image. |
| Question Answering | Provide accurate answers to questions based on a context or document. |
| Sentence Similarity | Compute the semantic similarity between sentences. |
| Summarization | Generate concise summaries from longer text. |
| Text Classification | Categorize text into predefined categories. |
| Text Generation | Generate coherent text based on a given prompt. |
| Text to Audio | Convert text into audio (speech synthesis). |
| Text to Image | Generate images from textual descriptions. |
| Text to Speech | Convert text to speech audio files. |
| Text to Video | Create video content from text prompts. |
| Text-to-Text Generation | Perform text transformation tasks like translation or rewriting. |
| Token Classification | Label tokens in a text sequence with appropriate tags. |
| Translation | Translate text from one language to another. |
| Unconditional Image Generation | Generate images without any specific conditions or prompts. |
| Video Classification | Classify video content into predefined categories. |
| Visual Question Answering | Answer questions based on the visual content of an image. |
| Zero-Shot Classification | Classify text without requiring task-specific training data. |
| Zero-Shot Image Classification | Classify images without requiring task-specific training data. |
| Zero-Shot Object Detection | Detect objects in images without requiring task-specific training data. |
Authorizations
Provide your API key as Key your-key-here in the Authorization header.
Response
200 - application/json