<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CAM++ on The road</title><link>https://kane.mx/tags/cam++/</link><description>Recent content in CAM++ on The road</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Tue, 28 Apr 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kane.mx/tags/cam++/index.xml" rel="self" type="application/rss+xml"/><item><title>Transcribing Long Podcasts and Meetings with FunASR</title><link>https://kane.mx/posts/2026/funasr-podcast-transcription-openclaw/</link><pubDate>Tue, 28 Apr 2026 00:00:00 +0000</pubDate><guid>https://kane.mx/posts/2026/funasr-podcast-transcription-openclaw/</guid><description>
&lt;p>Two recordings sat on my disk waiting to be turned into searchable text. A 4-hour 13-minute discussion from a TGO founders' group — eight speakers, Chinese, Zoom audio. A 1-hour 8-minute podcast episode (屠龙之术 Vol.94 × 知本论) where two hosts spent the whole hour dissecting &lt;a href="https://www.xiaoyuzhoufm.com/episode/69e0d423b977fb2c471ea30c">OpenClaw&lt;/a> — its positioning, the AI-agent narrative, and investors' reactions.&lt;/p>
&lt;p>Both were full of specific claims, speaker-attributed opinions, and Chinese brand terms I wanted to grep later. Neither would transcribe cleanly with the tools I tried first.&lt;/p>
&lt;p>&lt;a href="https://kane.mx/posts/2026/funasr-podcast-transcription-openclaw/">Read More&lt;/a>&lt;/p></description></item></channel></rss>