# Building a Local Voice Dictation Device with Raspberry Pi, Whisper, and Ollama

DevFeed: [Building a Local Voice Dictation Device with Raspberry Pi, Whisper, and Ollama](<https://devfeed.tech/articles/i-built-my-own-wisprflow-fully-local-under-50-and-it-types-into-any-computer-25154.md>)

Original publisher: [Read original article](<https://blog.droidchef.dev/i-built-my-own-wisprflow-fully-local-under-50-and-it-types-into-any-computer/>)

Author: Ishan Khanna

Published: 2026-03-16T20:55:45Z

Content type: tutorial

Language: en

Sources: [Ishan Khanna](<https://devfeed.tech/sources/ishan-khanna.md>)

Topics: [Raspberry Pi](<https://devfeed.tech/topics/raspberry-pi.md>), [Whisper](<https://devfeed.tech/topics/whisper.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [ASGI](<https://devfeed.tech/topics/asgi.md>), [Python](<https://devfeed.tech/topics/python.md>), [GPU](<https://devfeed.tech/topics/gpu.md>), [Windows](<https://devfeed.tech/topics/windows.md>), [CircuitPython](<https://devfeed.tech/topics/circuitpython.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [audio](<https://devfeed.tech/tags/audio.md>), [circuitpython](<https://devfeed.tech/tags/circuitpython.md>), [fastapi](<https://devfeed.tech/tags/fastapi.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llms](<https://devfeed.tech/tags/llms.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [python](<https://devfeed.tech/tags/python.md>), [raspberry-pi](<https://devfeed.tech/tags/raspberry-pi.md>), [transcription](<https://devfeed.tech/tags/transcription.md>), [whisper](<https://devfeed.tech/tags/whisper.md>), [windows](<https://devfeed.tech/tags/windows.md>)

## AI overview

This tutorial describes a local voice dictation device built with a Raspberry Pi Zero W, Raspberry Pi Pico, and an INMP441 microphone. Audio is sent over Wi-Fi to a Windows PC for Whisper transcription and Ollama text cleanup, then returned through a USB keyboard interface via a KVM switch. The author reports about $40 in hardware costs and under 700 milliseconds of end-to-end latency.

## Source excerpt

I spend most of my day talking to AI agents in the terminal. Claude Code, ChatGPT, aider -- you name it. And every time I have to type out a long, detailed prompt explaining what I want refactored, I think: why am I typing this when I could just say