I thought transcription was a solved problem.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
I thought transcription was a solved problem. Then I came back from KotlinConf with interviews recorded as two people speaking on a single audio track. Getting the words wasn’t the problem. Knowing who said what was. So when AssemblyAI suggested I try their API and its speaker identification capabilities, I had a very specific problem to throw at it. Could I build a CLI tool that would: Take an audio file as input. Transcribe the conversation. Identify the different speakers. Generate a summary. Write everything to a file. I started with AssemblyAI’s quickstart, configured their MCP serve
Posted by John Crickett (14k followers) 2 days ago · 13 likes · 1.1k views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: AssemblyAI.
More dev work like this
- I've been trying to explain something to a few people this week, and I want to just put… — @volatilemarkts
- Finding the right agent tool shouldn’t mean digging through random GitHub topics. — @DanKornas
- Anthropic is getting ready to release Opus 5.5 this Tuesday! — @vikktorrrre
- New: agent-browser Contact Sheets — @ctatedev
- Wafer just dropped an AI performance engineering repo that covers: — @Hesamation
- Feedback for Claude Code desktop team: — @rudrank
- I put together a container for anyone who wants to try out a Bonsai 2 27B "bjev" for DGX… — @mmastrac
- Probably by tomorrow I will release ai-memory version 2.4. This is possibly the largest… — @AkitaOnRails
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 17k posts from 4.9k X accounts over the last 21 days, 1.9k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-20 22:16 UTC. Full method.