Local AI workflow
Local transcription + summary pipeline
Voice notes and meetings to searchable text and summaries, fully offline: a local STT engine feeding a small LLM. The stack: whisper.cpp, faster-whisper with llama.cpp serving 2 recommended local models — hardware readiness graded by the same engine as the feasibility checker.
The stack
Hardware readiness
Each cell is the engine's verdict for the best clean quant of that model on llama.cpp at 8K context — the same math as the checker, tiers not numbers.
The readiness table below sizes the LLM half only. STT engines are their own runtimes with no rows in our feasibility dataset — each tool's page carries its sourced hardware note.
Different hardware? Check your exact machine against any model in this stack.
Check your machine →Don't have the hardware? Build a stack for your budget →Template picks are editorial; every verdict, grade and tier above comes from the engine over sourced data — how the math works.