(via SharewareOnSale)
AI Requester

AI Requester Giveaway

Vovsoft AI Requester is a program that can connect to OpenAI API and OpenAI-compatible APIs with ease.

The software provides a reliable and easy-to-use interface that seamlessly integrates with the latest AI technologies, including GPT-6-Astra, GPT-5, GPT-4o (omni), GPT-4-Turbo, o1, o3, and DALL-E.

Built for both offline and online environments, it allows you to experiment with leading models like DeepSeek, Qwen, Gemma, LLaMA, and Mistral using industry-standard text generation APIs:

• OpenAI-compatible endpoints: /v1/chat/completions and /v1/responses
• Anthropic-compatible endpoints: /v1/messages

Whether you’re exploring AI models locally without an internet connection or connecting to online services, this program offers a flexible environment to suit your needs. You can manually edit API settings models.json file, giving full control over multiple AI models without relying only on the GUI.

Vision feature allows the model to take in images and answer questions about them. You can easily utilize this feature by providing any PNG file or image URL.

You can input textual descriptions or prompts and generate corresponding high-quality images. The software leverages the state-of-the-art image synthesis capabilities of DALL-E, allowing you to bring your ideas to life with stunning visuals. The software supports generating 3840x2160, 2160x3840, 2048x2048, 2048x1152, 1792x1024, 1024x1792, 1536x1024, 1024x1536, 1024x1024, 512x512, and 256x256 images.

• Create Image: Creates an image given a text prompt.
• Create Image Variations: Creates a variation of a given image file.
• Edit Image: Creates an edited or extended image given an original image file and a text prompt. The original image must be a PNG file with transparency channel.
• Speech to text: You can input any audio file and turn audio into text. The following input file types are supported: wav, mp3, mp4, mpeg, mpga, m4a, and webm.
• Text to speech: You can input any text and convert into mp3 file with AI powered natural voices.