Chaining Small Models for Voice Cleanup

Logosofia no Dia a Dia · Sep 20, 2026 · 22m

Daniel's phone-based voice pipeline has the transcription part solved — it's the cleanup that falls apart. Dates render as "nineteen eighty-four," paragraphs have no boundaries, and self-corrections like "wait, I meant grapes" sit in the text as content. His instinct is to chain six or seven small models, each doing one narrow job. But every stage multiplies the error rate, and the destructive stages — like instruction scrubbing — can silently delete a user's words. This episode works through the real tradeoff: one multimodal model with a long system prompt versus ASR plus a chain of narrow…