
AI Engineering• 12 min
Assembly AI: Speech-to-Text at Scale
Real-time transcription architecture, speaker diarization, and cost optimization strategies for processing 1M+ minutes of audio — cutting our bill by 45%.
#assembly-ai#speech-to-text
4 posts

Real-time transcription architecture, speaker diarization, and cost optimization strategies for processing 1M+ minutes of audio — cutting our bill by 45%.

Building a Grok-inspired real-time knowledge graph system that ingests live data streams and answers questions with up-to-the-minute accuracy.

Real-time web retrieval, citation-grounded generation, and the architecture behind sub-second answers — building a Perplexity-style search engine.

Retrieval-based Voice Conversion for real-time voice conversion that preserves intonation and emotion while changing the speaker identity.