SuperAPI AI Directory
Partner中文AI newsFavorites

All AI tools

35,738 results · Page 534 of 993

Ant Directory

AI productivity

Ant Directory is an AI tool directory website designed to help users discover and filter software, applications, and resources that suit their needs, in order to boost productivity and streamline processes. The website offers browsing sorted by criteria such as time, and includes a variety of AI tools covering areas such as video generation, image editing, music creation, subtitle generation, and API platforms. The tool entries displayed in the directory include their respective names and brief descriptions, such as AI studio, video generation platform, image background removal tool, AI music video generator, pixel art asset generator, AI reply assistant, podcast production tool, and more, spanning multiple fields from creative content production to everyday efficiency. Ant Directory positions itself as resource discovery and navigation, emphasizing "discover the best tools for you," and mentions that the website has been checked. Users can explore broadly through the directory or category browsing, or find tools for a specific goal. Currently, the available information does not provide details such as its inclusion and review criteria, number of tools, pricing model, or account requirements, and these are not yet available.

Read more

antigravity-link-extension

AI coding

Antigravity Link is a VS Code extension that provides a mobile companion for Google's Antigravity IDE. By scanning a QR code, users can mirror the current AI session in real time on a mobile browser within the same local network, reading streaming output, sending messages, stopping generation, uploading files, using voice input, and switching between multiple Antigravity windows at any time. The extension also exposes a local HTTP API and an MCP server, including 9 MCP tools, making it easy for agents or external tools to drive Antigravity sessions programmatically. The extension only runs a local server on the local machine, uses token authentication and self-signed HTTPS, with all communication confined to the local network; it does not modify Antigravity files or intercept its network traffic. The interface supports 16 languages with automatic detection, including RTL support. The project uses the MIT license, and the source code is publicly auditable.

Read more

AnyFileKit

Other AI tools

AnyFileKit's image translator can translate text in images into English or a specified language in the browser, and render the translation back into the original image positions, outputting a full-size PNG. It supports screenshots, photos, scanned documents, comics, and more, can automatically detect the language, and covers Japanese, Korean, Chinese, Arabic, Thai, Hindi, and multiple European languages. It offers AI mode (default, uploads a reduced-size copy, images are counted as 2 pages) and Fast mode (images are read locally, only text is uploaded, reading does not count toward pages). No registration required, 5 pages free per day (3,000 characters per page). If you only need the text, you can use Image to Text to extract it with no daily limit.

Read more

anyimg.ai

AI images

anyimg.ai is a prompt-based AI image editor that completes image editing through natural language instructions. Core capabilities include: removing objects from the frame, replacing backgrounds, retouching portraits, restyling, and generating new images. The tool supports reading and preserving model pose and lighting, extracting clothing graphics and colors, checking the source consistency of generated results, and can modify only selected areas during editing while protecting composition, identity features, lighting, and unselected pixels unchanged. It supports uploading reference images of people, products, or brands, allowing the editor to extract key cues and output a stylistically unified editable image set. The editor provides a Version Trail feature, where every modification becomes a visible branch, allowing comparison of different directions, returning to the original version, or continuing to move forward. It supports models such as GPT Image 2, Nano Banana Pro, and Nano Banana 2, which can be switched per use or automatically selected by the agent. Registration comes with free credits, and paid plans start at $4.90 per month, including commercial licensing and unlimited downloads. Paid plans are billed by credits, with credit consumption varying by model and resolution. Credits are automatically refunded for failed tasks, and subscriptions can be canceled at any time in billing settings.

Read more

Anymelo

AI audio

Anymelo is an AI-based music generation tool that lets users create royalty-free music simply by entering a text description or lyrics, without needing music theory or production skills. The platform offers a complete AI music creation suite, including song generation, music extension, AI covers, music layering, vocal separation, and other features, with support for multiple music styles and multilingual vocal synthesis. The generated music can be used in commercial scenarios such as YouTube videos, podcasts, advertisements, games, and films (a Pro plan subscription is required to obtain full commercial rights). Users can download MP3, WAV, or stem files, and the creation process is fast and simple.

Read more

AnyModal

AI developer platforms

AnyModal is a modular multimodal language model framework based on PyTorch, used to connect pre-trained vision (or other modality) encoders with large language models through a pluggable projector architecture. It has 5 built-in projector architectures (Linear, MLP, Q-Former, Perceiver Resampler, C-Abstractor), supports any HuggingFace vision model such as ViT, SigLip, CLIP, DINOv2, is driven by YAML configuration, integrates HuggingFace Trainer, supports PEFT/LoRA, and provides pip installation and a type-annotated API. Users only need a configuration file and a small amount of code to train multimodal models.

Read more

AnySpeech

AI audio

AnySpeech is an AI text-to-speech platform for content creators that converts text into natural speech. It offers more than 100 realistic voices covering over 50 languages, and is suitable for scenarios such as YouTube videos, podcasts, audiobooks, online courses, marketing ads, accessible content, and app and game development. The platform supports a free trial and can be experienced without registration. In addition, AnySpeech also offers a voice cloning feature, which is said to be able to create a digital copy of a voice with only about 10 seconds of audio sample.

Read more