Gemini OmniFlash Generator

What it does

Gemini OmniFlash Generator helps creators explore AI video generation workflows using text, image, audio, and video inputs. It is designed for fast prompt testing, concept previews, and multimodal video creation experiments.

• 
  Gemini OmniMay 2026 · deepmind.google · ▲386

  Create anything from any input – starting with video

• 
  Gemini Omni Video GeneratorMay 2026 · ▲2

  AI video generator

• 
  Gemini Omni Video - AI Video GeneratorJun 2026 · geminiomnivideo.ai · ▲2

  AI video generator that works like a creative conversation

• 
  Gemini Omni VideoMay 2026 · geminiomnivideo.app · ▲1

  Create AI videos from text and images in seconds

• 
  Gemini Omni AIMay 2026 · gemini-omni-ai.com · ▲1

  Cinematic AI videos from prompts and multiple references

• 
  Free Gemini OmniJun 2026 · freegeminiomni.com · ▲4

  Create AI videos from text, images with Gemini Omni.

• 
  Clipto MCP▲640

  Let agents source clips from terabytes of your local video

  Work · 19d ago · clipto.com

• 
  HyNote for Mac▲383

  Free local transcription that is 100% Private

  Work · 18d ago · hynote.ai

• 
  VoiceOS App Store▲330

  The app store for voice native apps that lives in your notch

  Work · 29d ago · voiceos.com

• 
  Scrimba Explain▲325

  Ask any question, get a video back instantly

  Work · 25d ago · scrimba.com

• 
  Brew ▲905

  Like Claude design for email marketing

  AI · May 2026 · brew.new

• 
  Kilo Code for VS Code▲897

  Parallel agents, diff reviewer, and multi-model comparisons

  Dev tools · May 2026 · kilo.ai

• 
  StoreClaw▲805

  Grow your store profits with agents that know how to sell

  AI · May 2026 · storeclaw.ai

• 
  PollyReach▲796

  Give your agent a real number and voice to make calls.

  AI · May 2026 · pollyreach.ai

• NW
  Needle: We Distilled Gemini Tool Calling into a 26M Model▲776

  Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…

  Life & fun · May 2026 · github.com

• FM
  Files.md – Open-source alternative to Obsidian▲730

  Dev tools · May 2026 · github.com