“generate”的搜索结果

根据曲风、氛围和使用场景，通过 MiniMax music API 生成带人声歌曲或纯音乐，并保存为 MP3；可使用自备歌词，也可自动生成歌词。

• 为视频制作背景音乐
• 用自己写的歌词制作主题曲
• 生成无人声的纯音乐

Turn text into speech with ElevenLabs through Composio MCP. Browse voices, select speech models, check remaining credits, generate downloadable audio or stream it for playback, and retrieve previously generated recordings from history.

中文简介正在准备中。当前显示英语简介。

• Create narration from a script
• Compare available voices and their attributes
• Check remaining credits before bulk generation

Generate and edit images and videos through Atlas Cloud using one API key across multiple model families. Choose supported models for each task, download the results, and retain details about the model, inputs, and estimated cost.

中文简介正在准备中。当前显示英语简介。

• Generate images and videos through one service
• Edit product images using reference materials
• Create videos from images, video, or audio references

Generate images from written instructions and edit saved or uploaded images using them as references. Continue refining the latest image in a conversation, adjusting details such as brightness, background, or colors while specifying what to preserve.

中文简介正在准备中。当前显示英语简介。

• Creating an image from a written description
• Editing an uploaded image
• Refining the latest generated image

Generate images and videos through Atlas Cloud by checking each model’s input requirements before submission. Guides the agent through sending a request, checking progress within a time limit, and downloading and validating the resulting media.

中文简介正在准备中。当前显示英语简介。

• Generate an image from a text prompt with Atlas Cloud
• Generate a short video from a scene description
• Check model-specific inputs before submitting a request

Build and maintain a GitNexus code index, a searchable map of code relationships. Use CLI commands to refresh or remove indexes, check their status, list indexed projects, and generate repository documentation with an LLM.

中文简介正在准备中。当前显示英语简介。

• Create a code index for a new project
• Refresh the index after code changes
• Check, remove, or list existing indexes

Send crypto payments through Binance Pay using QR codes or payment links, then check payment status. Generate links and QR codes to receive payments, with support for C2C payments and automatic detection of PIX QR codes.

中文简介正在准备中。当前显示英语简介。

• Pay using a Binance Pay QR code
• Pay using a PIX QR code
• Generate a link to receive crypto

Compare GraphQL and RPC contracts, which describe expected API behavior, with generated clients and live handlers in a CTF sandbox. Identify hidden or outdated operations and preserve minimal request pairs that demonstrate the mismatch.

中文简介正在准备中。当前显示英语简介。

• Compare API contracts with live request handling
• Trace requests made by generated clients
• Investigate hidden or outdated API operations

Turn a browser scenario into a Playwright TypeScript test by first performing its steps through Playwright MCP. The skill saves the generated test in the tests directory, runs it, and revises it until it passes.

中文简介正在准备中。当前显示英语简介。

• Create an automated test from a browser scenario
• Turn an executed interaction flow into test code
• Run and fix a generated Playwright test

Integrate or upgrade cache-dit in SGLang diffusion, the image generation system. Follow guidance for resolving code conflicts, adding cache settings, testing feature combinations, and comparing generated images using quality measurements and logs.

中文简介正在准备中。当前显示英语简介。

• Upgrading cache-dit in SGLang diffusion
• Resolving conflicts when porting upstream changes
• Adding per-request cache settings

Launch an SGLang server, run a quick accuracy check, and capture an execution trace for performance inspection. Return the trace location and generated files, ready to open in Perfetto or Chrome tracing.

中文简介正在准备中。当前显示英语简介。

• Capture an execution trace of SGLang inference
• Check basic accuracy before profiling
• Record input processing and token generation separately

Generate images from written descriptions through 9Router using a choice of image models. Check each model’s supported settings, request an image, and receive a URL, encoded image data, or image bytes for saving to a file.

中文简介正在准备中。当前显示英语简介。

• Creating a landscape image from a written description
• Checking supported image sizes and quality settings
• Saving generated images as files

Ask AI questions, generate code, and summarize text through 9Router using OpenAI or Anthropic request formats. Receive responses incrementally with streaming, and use provider combinations that automatically try another provider when needed.

中文简介正在准备中。当前显示英语简介。

• Ask an AI model questions through 9Router
• Generate code from written instructions
• Summarize text with a selected model

Turn content into slides designed for reading and sharing. The skill creates an outline, generates individual slide images in a consistent style, and combines them into PPTX and PDF files for distribution.

中文简介正在准备中。当前显示英语简介。

• Turning an article into a shareable slide deck
• Creating illustrated learning materials for beginners
• Preparing a technical overview with a consistent style

Generate a client in your chosen language for live, two-way communication with Gemini Enterprise LiveAPI. Includes token renewal, session recovery, tests, and a demo interface for trying text, audio, video, and transcription.

中文简介正在准备中。当前显示英语简介。

• Build a client for live conversations with Gemini
• Add token renewal and session recovery
• Test audio and video input through a demo interface

Detect and check structured data, machine-readable descriptions of page content, and generate suitable Schema.org JSON-LD snippets. Get a report of missing fields, syntax errors, and markup issues, plus code prepared for implementation.

中文简介正在准备中。当前显示英语简介。

• Check existing structured data for errors
• Generate markup for products, articles, or businesses
• Review deprecated schema types

Plan and audit large sets of pages generated from structured data. Assess source quality, template uniqueness, URLs, and internal links, then identify thin content and unnecessary search indexing with prioritized recommendations and staged publishing guidance.

中文简介正在准备中。当前显示英语简介。

• Plan directory or glossary pages from structured data
• Audit repetitive content across generated pages
• Design URL patterns and automated internal links

Create model architecture diagrams and method illustrations for academic papers using Gemini. Codex plans the figure and reviews generated images for correct connections, content, layout, and readability, guiding repeated revisions toward a clearer final figure.

中文简介正在准备中。当前显示英语简介。

• Illustrate a model architecture for a paper
• Show a method's processing steps and data flow
• Create a conceptual comparison diagram

Prepare and launch Autoware with CARLA on UE 5.8 through its native ROS 2 interface. Check communication topics and sensors, generate required maps, and configure either the classical stack or camera-only VAD model.

中文简介正在准备中。当前显示英语简介。

• Check whether a CARLA build supports Autoware
• Inspect topics exchanged between CARLA and Autoware
• Generate lanelet2 and point-cloud maps for a town

Creates figures for machine learning papers from draft text or experiment data. Extracts components for Gemini-generated diagrams, chooses suitable charts with matplotlib or seaborn, and adjusts colors, fonts, and export formats for publication.

中文简介正在准备中。当前显示英语简介。

• Turn a method section into an architecture diagram
• Create comparison charts from experiment results
• Plot training loss and accuracy over time

Generate or update up to nine project documentation files using agents that inspect the code directly. Check documentation against the implementation, review existing files without writing changes, or explicitly regenerate all documentation.

中文简介正在准备中。当前显示英语简介。

• Create project documentation from the codebase
• Update documentation after implementation changes
• Check existing documentation without writing files

Create game assets through fal.ai, including sprites, textures, 3D models, sound effects, music, voices, and video clips. Guides consistent visual variations, file conversion, model selection, and generation records so assets can be traced and regenerated.

中文简介正在准备中。当前显示英语简介。

• Create transparent sprites and icons for a mod
• Generate seamless textures and material maps
• Build and rig a 3D character from an image

Describe photos, screenshots, and charts in text, generate images from written prompts, or edit existing images. Supports background replacement, transparent output, and edits limited to an area defined by a mask.

中文简介正在准备中。当前显示英语简介。

• Get a text description of a photo or screenshot
• Generate a landscape image from a written prompt
• Replace a photo background or change its style

Generate documents through shell scripts when standard tools fail, then locate files saved in nested folders. Covers finding PowerPoint or PDF outputs, copying them to the delivery location, and checking that the resulting files exist and are usable.

中文简介正在准备中。当前显示英语简介。

• Generate documents when standard tools fail
• Find PowerPoint or PDF files in nested folders
• Copy generated files to the delivery folder