Turn a script into narration
When you have text ready for a voiceover, generate speech with controls for voice, pace, pitch and emotion. A dedicated Japanese speech tool also supports Japanese narration.
Toolsminimax_japanese_
Overview
SynClub MCP Server gives an MCP-compatible assistant access to media generation, image editing, image analysis and search through SynClub APIs. It brings speech, voice cloning, video and comic creation into the same conversation, with tools for both creating new material and adapting existing assets.
The server runs on your computer and requires an API key from your SynClub account. Processing uses remote APIs: prompts and supplied media are sent to the service. Its tools can create media, save output files locally and create cloned voices; MiniMax generation calls may incur charges.
Use Cases
Create a voice from a recording
Use an audio sample when a preset voice does not fit your project. Voice cloning returns a voice ID and can produce demo audio; the cloned voice is charged on first use.
Toolsminimax_
Make a video from a concept
Describe a scene when you need a video without supplying source footage. Generate a clip from the prompt; Kling also provides a separate tool for checking the task and retrieving its result.
Toolskling_kling_minimax_sora_veo_
Animate an existing still image
Start with an illustration or other source image and describe the motion you want. Image-to-video tools turn that still into a clip, with Kling offering motion and camera controls.
Toolskling_kling_veo_
Create artwork from a written brief
When an idea has no source image yet, describe the subject and composition to generate artwork. Available tools offer different models and output proportions, including portrait, landscape and square images.
Toolsopenai_minimax_flux_google_google_
Revise an image with written instructions
Supply existing images and describe the changes you need to get edited versions. Depending on the tool, you can work from one image, several references or a batch of image URLs.
Toolsopenai_flux_flux_google_google_
Extract a subject from its background
When you need the foreground objects from an existing image for another composition, provide its URL to remove the background and obtain the extracted result.
Toolsremove_
Restore a low-quality image
When an image needs better quality or resolution before reuse, submit its URL for high-definition restoration and receive the processed image.
Toolshd_
Develop a comic from a story idea
Turn a theme or novel into comic scripts and chapters, revise the writing, and develop image prompts and comic illustrations. This helps take a story concept into written and visual comic material.
Toolsgenerate_edit_generate_edit_generate_anime_anime_
Develop character artwork and presentation images
Create an anime character from a written description, or adapt existing character art into three-view references, meme packs, character cards or figure-style presentation images.
Toolsugc_google_
Ask questions about an image
When you need to understand an image's content, supply its URL and a question describing what to examine. The image analysis tool returns a response guided by that question.
Toolsopenai_
Look up information through your assistant
For a question that needs search results, submit a query with a choice of search engine, AI model and response language to receive an AI-assisted search response.
Toolsai_
Tools
These tools were captured on August 11, 2026; check your client's tool list for availability.
Showing all 33
Image creation and editing
flux_edit_image
Edits an image supplied by URL using an English prompt.
flux_pro_edit_image
Edits images with Flux Pro using an English prompt and up to four source images, with a choice of output aspect ratio.
flux_pro_tti
Creates an image from a text prompt with Flux Pro, with a choice of portrait, landscape or square proportions.
google_nano_banana_pro_generate_image
Creates images from text or up to 14 reference images with Google Nano Banana Pro. Supports Chinese and Japanese text rendering and output sizes of 1K, 2K or 4K.
google_nano_edit_image
Edits existing images from a text description of the desired changes. Accepts multiple image URLs for batch processing.
google_nano_tti
Creates an image from a text prompt using Google Nano.
hd_restore
Restores image quality and resolution from an image supplied by URL.
minimax_text_to_image
Creates and saves one to nine images from a prompt using MiniMax, with a choice of aspect ratio. API calls may incur charges.
openai_edit_image
Edits images supplied by URL according to a text prompt using an OpenAI model.
openai_generate_image
Creates one to nine images from a text prompt and returns image URLs or file paths.
remove_bg
Removes an image's background and extracts its foreground objects from an image supplied by URL.
Comics and characters
anime_comic_image
Creates comic images from an English prompt and character pose references, with scenes containing no characters, one character or two characters. A first character reference image is required even for a scene with no characters.
anime_pose_align
Creates a pose reference from an existing anime character image for use in comic image generation.
edit_comic_chapters
Revises existing comic chapters according to an editing prompt, using chapter content that includes scene descriptions, dialogue and narration.
edit_comic_story
Revises a comic story and its title according to an editing prompt.
generate_comic_chapters
Turns a novel and character information into comic chapters. Generates four chapters by default, with a maximum of 15.
generate_comic_image_prompts
Turns comic chapter content and character information into prompts for generating comic images.
generate_comic_story
Drafts a comic script from a topic or theme, including topics written in Japanese.
google_nano_edit_image_highlight_feature
Transforms character images into one of four formats: three orthogonal views, a nine-panel meme pack, an original-character display card or a realistic image of a 1/7-scale figure.
ugc_tti
Creates an anime character from an English description, with a choice of character gender and game, anime, manhwa, comic or illustration style.
Video creation
kling_generate_image_to_video
Creates a Kling video from a source image and a text prompt, with controls for motion, masks and camera movement. May return a task ID; kling_query_itv_task checks progress and retrieves the result.
kling_generate_text_to_video
Creates a Kling video from a text prompt, with controls for camera movement and content to avoid. May return a task ID; kling_query_ttv_task checks progress and retrieves the result.
kling_query_itv_task
Checks a Kling image-to-video task by its task ID and returns its progress, result URL or error details.
kling_query_ttv_task
Checks a Kling text-to-video task by its task ID and returns its progress, result URL or error details.
minimax_generate_video
Creates and saves a MiniMax video from a prompt, with an optional first-frame image for I2V models. Director models also accept camera movement instructions. API calls may incur charges.
The default mode waits for the result. Asynchronous mode returns a task ID, but the status-checking tool it names is absent from the collected tool list.
sora_generate_text_to_video_
Creates a Sora 2 video from a text prompt in landscape or portrait format. Supports durations of 4, 8 or 12 seconds and returns a video URL or task ID.
veo_generate_image_to_video
Creates a video with audio support using Google Veo, a text prompt and one source image or a pair of first- and last-frame images. Supports landscape and portrait formats and returns a video URL or task ID.
veo_generate_text_to_video
Creates a video from a text prompt using Google Veo, with audio support and a choice of landscape or portrait format. Returns a video URL or task ID.
Speech and voice cloning
japanese_tts
Converts Japanese text to speech, with selectable audio format, sample rate and voice gender. Supports Japanese text only.
minimax_text_to_audio
Converts text to speech with controls for voice, speed, pitch, volume and emotion, then saves an audio file. API calls may incur charges. Without an output directory, the file is saved to $HOME/Desktop on the computer running the server.
minimax_voice_clone
Creates a cloned voice from an audio file or URL and returns its voice ID, with optional demo audio. API calls may incur charges, and the new voice is charged on first use.
Search and image analysis
ai_search
Searches for information using a chosen search engine and AI model, with a selectable response language.
openai_image_recognition
Analyzes an image supplied by URL using GPT, guided by a prompt describing what to examine.
No matching results.
Install
Have uv installed and a SynClub API key ready before configuring your MCP client.
Installation categoriesConnect to your AI tool
Claude Desktop
- 01
Prepare uv and your API key
Install uv using the README’s installation instructions, and make sure
uvxis on PATH.Have your SynClub API key ready. The project directs you to your account information page on the SynClub server website to obtain it.
- 02
Add SynClub to Claude Desktop
In Claude Desktop, open Settings → Developer → Edit Config to open your JSON configuration file. Add the
SynClubentry undermcpServers, keeping any existing server entries. Replaceyour api keywith your SynClub API key inSYNCLUB_MCP_API, then save the file.claude_desktop_config.jsonJSON{ "mcpServers": { "SynClub": { "command": "uvx", "args": [ "synclub-mcp" ], "env": { "SYNCLUB_MCP_API": "your api key" } } } } - 03
Restart Claude Desktop
Quit and reopen Claude Desktop to load the saved configuration.
Check the result
Open Settings → Developer in Claude Desktop and check the connection status for SynClub.
SynClub MCP Server setupConnect local servers to Claude Desktop