One page: the three recording branches (client / per-participant / mixed), the ASR audio path (16 kHz, 80 log-mel bands, Whisper), live-caption latency, and the questions to ask before audio leaves the call.
Download free PDF
The book · Volume 6 of 7
AI for Video: A Complete Guide to Intelligence in Video Products: From Models and Inference to Computer Vision, Speech, Search, and Generative Video
This recording and transcription field guide covers the three recording branches, the ASR audio path into Whisper, live caption latency and the questions to ask before audio leaves the call. Volume 6 covers this topic in depth: speech recognition, diarization and TTS, deployment topologies, model artifacts and search over recorded video. Written by Nikolay Sapunov, CEO at Fora Soft.
Adding recording and transcription to your calls and need accurate transcripts?
Share your call setup and languages, and we will design the recording branch and ASR pipeline and estimate cost per hour. 250+ video products shipped since 2005.
You get a realistic estimate, technical recommendations and next steps. Free, no obligations.
