Sagittarius
A web demo that lets you speak to an AI and ask what it recognizes, including hand gesture
Sagittarius is a browser-based demo that lets users speak to an AI model and ask it to identify what it sees, including hand gestures. It combines dictation and speech input with visual recognition, so users can talk to the model about their camera view in real time.
The demo supports dictation and speech across a wide range of languages and regional variants. It uses OpenAI's gpt-4-vision-preview and Google's gemini-pro-vision models, and its source code is available on GitHub. The page notes that it is best experienced using Google Chrome on desktop.
Sagittarius appears to be aimed at developers and users exploring voice-driven visual AI interactions. No pricing, plans, or editions are indicated on the page.
12 alternatives to Sagittarius
Ranked by how well each tool replaces Sagittarius: shared features, audience, price and popularity.
Understand your world and communicate across languages
Covers 1 of 6 key features.
Free plan57 out of 100 matchFreeOur mission is to build AI responsibly to benefit humanity.
Covers 0 of 6 key features.
Free plan50 out of 100 matchFree- 49 out of 100 matchFree
Speech-to-text and speech understanding APIs for voice AI applications
Covers 0 of 6 key features.
Free plan48 out of 100 matchContact sales- 48 out of 100 match—
- 45 out of 100 matchUsage-based
Conversation intelligence and transcription for teams, with custom AI applications.
Covers 0 of 6 key features.
Free plan45 out of 100 match$20/moAI agents hallucinate, fix it faster.
Covers 0 of 6 key features and is open source.
Free planOpen source44 out of 100 match$250/moFree AI visibility checker. See how ChatGPT, Gemini, Perplexity and Google AI Overviews
Covers 0 of 6 key features.
Free plan42 out of 100 match$9.99/moChat with multiple AI models and hand off projects to an AI work agent that produces files
Covers 0 of 6 key features.
Free plan41 out of 100 match$16.67/mo