model
Speech-to-text model family used first through OpenAI's and Groq's hosted APIs and then self-hosted via faster-whisper.
No evidence-backed relationships are recorded.
The gap is documented rather than debatable. A vendor's own survey adds the numbers: four parallel-agent tools shipped in the past year, none of them running natively on Windows.
Reality
ArmBench-ASR v0.1 ranks nearly 30 systems on 20.7 hours of Armenian audio. The headline order flips on read speech, and every model degrades badly on movie dialogue.
Reality
A dev.to writeup argues Whisper is a batch model retrofitted for streaming. If your response budget is under a second on mid-range phones, that is a build decision, not a tuning exercise.
Reality
A dev.to deep dive puts caller context in FreeSWITCH's control channel, which never touches RTP. The media path stays clean, but conversational latency still needs covering.
Reality
One developer's day-one postmortem is really a dependency inventory: a single third-party call sat under every write and read path, and the fix moved the dependency rather than removing it.
Reality