Knowledge graph

Ask your meetings anything, with embeddings on our own server

Semantic search across your entire AudioMap library with embeddings computed on our own server in Europe (bge-m3). Ask "what did client X say about pricing?" and get answers with exact note + timestamp citations.

Try for freeSee pricing
🇪🇺

Embeddings on our own server in Europe

bge-m3 (1024 dims) on Hetzner DE. By default, embeddings are computed on our own server, not by OpenAI. Vector search via pgvector on the same Postgres.

🔍

Cross-library questions

Ask "which clients mentioned a price increase?" across all your notes. AudioMap finds them with citations.

📍

Timestamp citations

Every answer cites note + exact second. Click and AudioMap jumps to that segment. No "trust the AI": verify what was said.

🎯

Per-note chat

Or scope your question to a single recording. Useful for asesorías reviewing a specific client meeting.

🌐

MCP server

Connect your AudioMap library to Claude, ChatGPT, Cursor or Gemini. Use them as your memory.

⚡

Fast even at scale

pgvector + cosine similarity scales to thousands of meetings without external vector DB. Sub-200ms typical query latency.

Why bge-m3 instead of OpenAI text-embedding-3?+

bge-m3 (BAAI) is multilingual (100+ languages including all Spanish variants), open-source, and runs entirely on our Hetzner DE server. Quality is comparable to text-embedding-3-large for Spanish. By default we use bge-m3 instead of OpenAI so that embeddings are computed on our own server.

How big can my library be?+

pgvector handles millions of segments efficiently with HNSW index. Practical limit is your disk, not the engine. We've tested with 500K+ segments in single-digit-second query latency.

Can I ask questions in English about Spanish recordings?+

Yes. bge-m3 is cross-lingual: the embedding for "what did Sara say about budget?" in English matches Spanish content discussing "presupuesto". Cross-language retrieval works both directions.

How does MCP work?+

Generate an API key at /dashboard/api-keys, configure your Claude/ChatGPT/Cursor with our MCP server URL, and they can query your AudioMap library directly. Tools: search_notes, get_transcript_segments, ask_note, etc. Free tier includes 200 credits/month MCP usage.

You may also like

vs Granolavs Firefliesvs Ottervs Supernormal
AI transcription
Hybrid EU transcription with Spanish variants
Deliverables from notes
Generate emails, docs and slides from any meeting

Turn your library into your memory

Semantic search included from Free tier. 300 free minutes monthly. Embeddings on our own server.

Try for free