Speaker Diarization Explained: How AI Adds Speaker Labels to a Transcript
Speaker diarization is how AI works out who said what in a recording — automatically labelling each speaker in your transcript. This guide explains how diarization works, why it matters for interviews, meetings and research, and how to get clean, accurate speaker labels.
KKevin Wong
2026-06-01
How to Transcribe a Zoom Meeting Into a Clean Transcript and AI Summary
Zoom can transcribe your meetings, but the good transcript is locked behind a paid plan and cloud recording, the summary needs AI Companion, and a recent change means you can no longer save the live captions. Here's exactly what Zoom does on its own, where the walls are, and how to record a call and turn it into a clean multilingual transcript plus a structured summary in Subanana.
KKevin Wong
2026-06-01
Academic Transcription: How to Choose a Tool for Lectures, Interviews, and Dissertations
Academic transcription turns lectures, research interviews, and dissertation recordings into text you can quote, code, and cite. This buyer's guide compares manual typing, AI speech-to-text, and human transcription on accuracy, speaker labels, export, and cost — and shows when AI is enough and when it isn't.
KKevin Wong
2026-06-01
Content Repurposing: Turn a Video or Podcast Into Blog Posts and Newsletters
The fastest way to repurpose a video or podcast into a blog post, newsletter, or show notes is to start from an accurate transcript and edit down from there. This guide walks through the transcript-first repurposing workflow — capture, outline, rewrite — and shows how to produce a clean, quotable transcript with Subanana's transcript mode so the raw material is something you can actually reuse.
KKevin Wong
2026-06-01
Qualitative Research Transcription: A How-To for Interviews and Focus Groups
Qualitative research transcription means turning interview and focus-group recordings into speaker-labelled, timestamped text you can code line by line. This guide explains why auto-captions fall short for analysis, how to choose between verbatim and intelligent verbatim, and a practical workflow using Subanana's transcript mode to get a transcript that drops cleanly into your coding software.
KKevin Wong
2026-06-01
Best AI Meeting Assistant 2026: Fathom vs Otter vs Fireflies vs Subanana
An honest, documentation-based comparison of four AI meeting assistants — Fathom, Otter, Fireflies, and Subanana — across accuracy approach, language coverage, summary quality, integrations, and pricing. Every figure comes from each tool's published docs.
KKevin Wong
2026-06-01
How to Translate a Video Into Another Language (Subtitles in 80+ Languages)
To translate a video, transcribe its speech, then generate translated subtitles in your target language — and export them as an SRT file or a burned-in video. This guide walks through the full workflow, when AI translation is good enough versus when it needs a human edit, and how to do it for one or several languages at once.
KKevin Wong
2026-06-01
Subanana vs Circleback (2026): A Documentation-Based Comparison for Action-Item-Focused Meeting AI
Circleback is a meeting AI assistant focused on action-item extraction and automated follow-up workflows. This compares Circleback and Subanana on pricing, language support, integrations, and AI summary — based on each tool's published documentation.
KKevin Wong
2026-05-31
Best Wordly Alternatives 2026: Honest Roundup of Live Translation Tools
A documentation-based roundup of Wordly alternatives for live multilingual captioning and translation — KUDO, Interprefy, built-in platform translation, and Subanana. Pricing models, language coverage, and where each fits.
KKevin Wong
2026-05-31
How to Add Subtitles in After Effects (2026 Guide)
After Effects has no built-in speech-to-text and no native SRT import. This guide covers the four real workflows for adding subtitles in AE 26, ranked by setup time and total cost, and shows where each one breaks.
KKevin Wong
2026-05-31
How to Add Subtitles in Final Cut Pro (2026): The Full Workflow + AI-SRT Workaround for Non-English Content
Final Cut Pro 12.2 added on-device Transcribe to Captions in 2024 — but Apple's documentation supports English-language audio only. This walks the native Final Cut Pro caption workflow (including the new English STT), where it falls short for Cantonese, Mandarin, Japanese, and mixed-language video, and the AI-generated SRT method that fills that gap.
KKevin Wong
2026-05-31
Live Captions for Multilingual Events (2026): A Practical Guide
Built-in Zoom / Google Meet captions cover the basics for an English-only meeting. They don't cover the harder case: a conference with attendees who speak different languages, where each person needs the live captions in their own language on their own device. Here's how that actually works, and the tools that make it practical without a five-figure enterprise contract.
KKevin Wong
2026-05-31