AI Media Generation
AI media generation contains AI Image , Video and Audio generation.
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение
Что умеет
- Health: Health check endpoint to verify server is running. Returns: A simple health status message
- Check Token: Check the current user's token status and account information. This tool retrieves information about: - User ID - Paid account status - Remaining generation tokens (for non-paid users) -
- Generate Image: Input: A textual input in prompt provide by user in the form of image prompt. Output: We will return the image url output to the user. Functionality: This tool is used to generate an i
Какие данные видит
Нужен ли аккаунт
Не нужен: сервер работает без входа
AI media generation contains AI Image , Video and Audio generation. All of this things can be generated simulatenously
Список инструментов сервера (17)
Технические названия из tools/list. Нужны только разработчикам.
| health | Health check endpoint to verify server is running. Returns: A simple health status message |
| check_token | Check the current user's token status and account information. This tool retrieves information about: - User ID - Paid account status - Remaining generation tokens (for non-paid users) - Account validity Returns: A JSON string containing token status and account information |
| generate_image | Input: A textual input in prompt provide by user in the form of image prompt. Output: We will return the image url output to the user. Functionality: This tool is used to generate an image based on a text prompt. User will provide a prompt and the tool will generate an image based on the prompt. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Generate Image API with the prompt provided by the user. 4. This Generate Image API will return a JSON response with the image url. 5. We will return the image url to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameter 'prompt' (type: string) from the user's provided prompt. The prompt should describe the image to generate. - Ignore any extraneous information in the user's input. - Pass the extracted 'prompt' value to this tool as the 'prompt' parameter. - Do not require the user to specify parameter names; extract the value from natural language. - Example: For user input "Generate an image of a cat in a spacesuit on Mars", extract 'cat in a spacesuit on Mars' as the prompt. |
| upscale_image | Input: An image URL and an optional scale factor (between 2 and 4) for upscaling. Output: We will return the upscaled image URL to the user. Functionality: This tool is used to upscale an image to a higher resolution. User will provide an image URL and optionally a scale factor, and the tool will return an upscaled version of that image. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Image Upscaler API with the provided image URL and scale factor. 4. This Image Upscaler API will return a JSON response with the upscaled image URL. 5. We will return the upscaled image URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameter 'image_url' (type: string, URL) and the optional parameter 'scale_factor' (type: integer, default 2, allowed values: 2-4) from the user's prompt. - If 'scale_factor' is not specified in the prompt, use the default value 2. - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool as 'image_url' and 'scale_factor'. - Example: For user input "Upscale this image https://example.com/image.jpg by 4x", extract 'image_url' as 'https://example.com/image.jpg' and 'scale_factor' as 4. |
| remove_background | Input: An image URL for background removal. Output: We will return the image URL with background removed to the user. Functionality: This tool is used to remove the background from an image. User will provide an image URL and the tool will return the image with the background removed. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Background Remover API with the provided image URL. 4. This Background Remover API will return a JSON response with the processed image URL. 5. We will return the processed image URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameter 'image_url' (type: string, URL) from the user's prompt. - Ignore any extraneous information in the user's input. - Pass the extracted value to this tool as 'image_url'. - Example: For user input "Remove the background from this image https://example.com/image.jpg", extract 'image_url' as 'https://example.com/image.jpg'. |
| logo_generator | Input: A text prompt describing the desired logo style. Output: We will return the URL of the generated logo image. Functionality: This MCP tool generates a logo using the provided text prompt. It leverages the Logo Generation API to interpret the prompt and create a corresponding logo image. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Logo Generation API with the provided prompt. 4. This Logo Generation API will return a JSON response with the logo image URL. 5. We will return the logo image URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameter 'prompt' (type: string) from the user's provided prompt. The prompt should describe the desired logo style or content. - Ignore any extraneous information in the user's input. - Pass the extracted 'prompt' value to this tool as the 'prompt' parameter. - Example: For user input "Create a logo for a vegan bakery with green leaves", extract 'vegan bakery with green leaves' as the prompt. |
| image_to_video | Input: An image URL and a descriptive prompt detailing the desired video scene. Output: We will return the generated video URL to the user. Functionality: This tool converts a static image into a dynamic video. The provided image serves as the base, while the accompanying prompt guides the AI on how to animate the image into a video that reflects the described scene. It leverages the Image-to-Video API to synthesize video content based on these inputs. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Image-to-Video API using the provided image URL and descriptive prompt. 4. The API processes the inputs and returns a JSON response containing the video URL. 5. We extract and return the video URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameters 'image_url' (type: string, URL) and 'prompt' (type: string, describing the desired video scene) from the user's prompt. - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool as 'image_url' and 'prompt'. - Example: For user input "Animate this image https://example.com/image.jpg to show a sunrise over the mountains", extract 'image_url' as 'https://example.com/image.jpg' and 'prompt' as 'sunrise over the mountains'. |
| generate_video | Input: A textual input in prompt provided by user describing the video scene to be generated. Output: We will return the video URL output to the user. Functionality: This tool is used to generate a video based on a text prompt. User will provide a detailed description of the scene and the tool will generate a video based on that description. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Text to Video API with the prompt provided by the user. 4. This Text to Video API will return a JSON response with the video details including URL. 5. We will return the video URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameter 'prompt' (type: string) from the user's provided prompt. The prompt should describe the video scene to generate. - Ignore any extraneous information in the user's input. - Pass the extracted 'prompt' value to this tool as the 'prompt' parameter. - Example: For user input "Generate a video of a robot dancing in a city at night", extract 'robot dancing in a city at night' as the prompt. |
| video_to_audio | Input: A muted video URL along with a textual prompt describing the desired audio. Output: We will return the video URL with the applied audio. Functionality: This tool now takes a muted video and a text prompt as input. It generates an audio track based on the provided prompt and applies this audio to the video, resulting in a video with integrated sound. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Audio Application API with the muted video URL and the provided prompt. 4. The API will generate the audio from the prompt and merge it with the muted video, returning a JSON response with the updated video URL. 5. We will return the updated video URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameters 'video_url' (type: string, URL) and 'prompt' (type: string, describing the desired audio) from the user's prompt. - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool as 'video_url' and 'prompt'. - Example: For user input "Add dramatic orchestral music to this video https://example.com/video.mp4", extract 'video_url' as 'https://example.com/video.mp4' and 'prompt' as 'dramatic orchestral music'. |
| get_music_categories | Input: No input required. Output: Returns a JSON string containing all available music categories with their IDs and descriptions. Functionality: This tool fetches all available music categories from the API. It can be called before music generation to help the LLM choose the most appropriate category. Returns: A JSON string containing music categories with their IDs, names, and descriptions INSTRUCTION FOR CLIENT MODEL: - This tool requires no input parameters. - Call this tool before music generation to get available categories. - Use the returned categories to make informed decisions about which category to use for music generation. |
| music_generator | Input: A text prompt describing the desired music and a music category ID and duration in seconds which needs to be in between 0 to 30 seconds which is optional and defaults to 15 seconds if not provided. Asking User to set the duration in seconds is optional. Output: We will return the generated music URL to the user. Functionality: This tool generates music based on a text prompt and selected music category ID. It follows these steps: 1. Gets user_id from context and validates tokens. 2. Generates music using the prompt and category ID. 3. Retrieves the final music URL from the queue. Args: prompt: Text description of the desired music music_category_id: The ID of the music category (integer) Returns: The URL of the generated music file INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameters 'prompt' (type: string, describing the desired music) and 'music_category_id' (type: integer) from the user's prompt. - The music_category_id should be a valid integer ID from the available categories. - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool as 'prompt' and 'music_category_id'. - RECOMMENDATION: Call get_music_categories() first to see available category IDs before choosing a music_category_id. - Example: For user input "Create a jazz song about summer rain with category ID 5", extract 'prompt' as 'about summer rain' and 'music_category_id' as 5. |
| song_generator | Input: Lyrics text and required tags (music categories/genres) for song generation. Output: We will return the generated song URL and details to the user. Functionality: This tool generates a custom song from provided lyrics. It creates original music that matches the style, mood, and tone specified by the tags. Tags must include music categories such as "rock", "pop", "jazz", "hip hop", "country", etc. Steps: 1. We will get the user_id from the request context. 2. We will validate the user's generation tokens. 3. We will call the Lyrics to Melody API with the provided lyrics and parameters. 4. This API will return a JSON response with the generated song URL and details. 5. We will return the song URL and details to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameters 'lyrics' (type: string) and 'tags' (type: string, music categories/genres). - Tags must include music categories like "rock", "pop", "jazz", "hip hop", "country", "electronic", etc. Multiple tags can be combined (e.g., "rock pop" or "jazz blues"). - Optional parameters: 'title' (default: "Melody"), 'language' (default: "English"), 'country' (default: "US"), 'audio_duration' (default: 0), 'ref_file_url' (reference audio URL, optional), 'ref_audio_strength' (0.0-1.0, default: 0.0). - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool. - Example: For user input "Create a rock song with these lyrics: 'Walking in the rain, feeling the pain'", extract 'lyrics' as 'Walking in the rain, feeling the pain' and 'tags' as 'rock'. |
| get_languages | Input: No input required. Output: Returns a JSON string containing all available languages. Functionality: This tool fetches all available languages from the API. |
| text_to_speech | Input: Text to convert to speech, language ID, and voice type. Output: Returns the URL of the generated audio file. Functionality: This tool converts text to speech in the specified language and voice. It follows these steps: 1. Gets user_id from context and validates tokens. 2. Generates speech from the text using the specified language and voice. Args: text: The text to convert to speech language_id: The language ID (defaults to "en" for English) voice_id: The voice type (defaults to "female") Returns: The URL of the generated audio file INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameter 'text' (type: string) and optional parameters 'language_id' (type: string, default 'en') and 'voice_id' (type: string, default 'female') from the user's prompt. - If 'language_id' or 'voice_id' are not specified, use the default values. - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool as 'text', 'language_id', and 'voice_id'. - RECOMMENDATION: Call get_languages() first to see available language IDs before choosing a language_id. - Example: For user input "Convert 'Hello world' to French with a male voice", extract 'text' as 'Hello world', 'language_id' as 'fr', and 'voice_id' as 'male'. |
| edit_image_with_text | Input: An image URL and a text prompt describing the desired edit (e.g., "change background to blue"). Output: The URL of the edited image. Functionality: This MCP tool edits an existing image based on a text instruction. It's useful for making changes like altering colors, adding or removing objects, or changing the style of an image. Steps: 1. Get the user_id from the request context and validate tokens. 2. Call the Edit Image API with the provided image URL and text prompt. 3. The API will return a JSON response containing the URL of the newly edited image. 4. Return the edited image's URL to the user. INSTRUCTION FOR CLIENT MODEL: - Extract the required input parameters 'prompt' (type: string, describing the desired edit) and 'image_url' (type: string, URL) from the user's prompt. - Ignore any extraneous information in the user's input. - Pass the extracted values to this tool as 'prompt' and 'image_url'. - Example: For user input "Change the background of https://example.com/image.jpg to blue", extract 'image_url' as 'https://example.com/image.jpg' and 'prompt' as 'change background to blue'. |
| search | Search for tools and resources available in the Saifs AI MCP server. This tool allows ChatGPT to discover available tools and their capabilities. It searches through tool descriptions, names, and functionality to find relevant tools. Args: query: The search query to find relevant tools Returns: A JSON string containing search results with tool information |
| fetch | Fetch detailed information about a specific tool or resource. This tool allows ChatGPT to get detailed information about a specific tool, including its parameters, usage examples, and functionality. Args: resource: The name of the tool or resource to fetch information about Returns: A JSON string containing detailed information about the requested resource |