Weaviate shows how to retrieve audio directly with Gemini Embedding 2
eshorten300 · x · 2026-07-28
Weaviate shares a notebook showing how to skip transcripts and retrieve audio directly with Gemini Embedding 2.
The workflow is:
- split raw audio into overlapping chunks
- build multimodal embeddings with Gemini Embedding 2
- store and search the clips in Weaviate
- retrieve relevant segments with text or audio queries
- generate grounded answers with Gemini 3 Flash
The example uses Robert Frost’s Birches, but the same pattern is positioned for podcasts, interviews, lectures, and call recordings.
More from Multimodal
- Flying car concept v2: Grok Imagine stills + MiniMax H3 video generation — creatoroff · 2026-10-16
- Flying car short made with Grok Imagine, Minimax H3 and Topaz upscale — creatoroff · 2026-10-16
- Fish Audio's open-weight Drama 3 voice model claims top emotive quality across 83 languages — mhdfaran · 2026-10-16
- Claude Opus 5.5 makes a pure-code Halloween animation starring bots trick-or-treating for tokens — sattvi · 2026-10-16
- 1,290-line commit lands MOSS Image support in ostris/ai-toolkit — ostrisai · 2026-10-16
- Ostris AI Toolkit adds training support for OpenMOSS's MOSS-Image-SFT model — ostrisai · 2026-10-16