Dikaletus – meeting recording and transcription using Mistral AI

Name: Dikaletus – meeting recording and transcription using Mistral AI
Availability: InStock
Author: phillc73

by phillc73·May 9, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidNiche GemCozy

Dual-channel audio capture via PulseAudio is a genuinely useful detail most wrappers miss.

Strengths

•Captures both mic and speaker output simultaneously for complete context.
•Written in R with a full test suite, which is rare for this language.
•Local TUI interface avoids browser overhead and keeps workflow in terminal.

Weaknesses

•Linux-only dependency on PulseAudio excludes Windows and macOS users entirely.
•Mistral API costs add up quickly compared to local Whisper models.

Post Description

Dikaletus is a TUI tool to record, transcribe, and generate structured meeting notes using FFmpeg, PulseAudio and the Mistral AI API.

The meeting agent automates the process of capturing, transcribing, and generating structured meeting notes. It records audio from both microphone and speaker outputs, transcribes the audio using Mistral's speech-to-text API, and generates structured meeting notes in Markdown format.

Years ago I used to write a lot of R code for data analysis. Then life changed and I wasn't doing that anymore. However, I still had small product ideas that required coding, but no time to do it. Dikaletus is my first vibe coded app, scratching one of those itches (I'm terrible at taking meeting notes in general).

Written in R, because that's what I know. Tried to following good practices with linting and testing.