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
- Practical Krea2 inpainting workflow pairs LanPaint with differential diffusion — Altruistic_Tax1317 · 2026-07-29
- Scobleizer says AI twins could let creators appear in 39 languages after one recording — Scobleizer · 2026-07-29
- Claude Code plus Blender MCP turns game building into Judge Driven Development — ccerrato147 · 2026-07-29
- Qwen3.6-35B uncensored GGUF variant starts trending on Hugging Face — LuffyTheFox · 2026-07-29
- Surrealscape images lean into impossible landscapes and editorial-fashion AI aesthetics — OVolosin82152 · 2026-07-28
- A manga creator says background consistency is harder than characters in NoobAI workflows — Boubbay · 2026-07-28