This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Cobalt InFX
On-device transcription & summaries that know who said what
Vox Dictum is a private, on-device transcription app for macOS. Transcribe recordings, tag speakers, and generate AI summaries — 100% on your Mac. No cloud. No data collection.
Hi Product Hunt — I'm Ozair, a programme director by trade. For twenty years I've been running large technology programmes, recording workshops, interviews, and stakeholder sessions along the way. The same problem kept coming back: I'd have hours of recordings and no practical way to turn them into usable notes without either spending an evening transcribing or uploading confidential client conversations to a cloud service.
I built Vox Dictum to fix that. It runs entirely on your Mac — no cloud, no accounts, no data leaving the device. You drop in a recording and get back a transcript with speaker names attached, plus an AI-generated summary with key decisions, action items, and topics covered. It supports 57 languages including Urdu, Arabic, and Hindi — all processed on-device.
The technical stack: WhisperKit for transcription, Pyannote for speaker diarisation, and Qwen3 for on-device summarisation, all running on Apple Silicon via MLX. The whole pipeline is local — privacy isn't a policy, it's the architecture.
The free tier is genuinely usable — unlimited transcription, speaker labelling, editing, and export. No trial, no nag screens. Pro adds larger models, AI summaries, and overlap resolution.
I'm a solo developer shipping this from London. Happy to answer any questions about the tech, the approach, or the journey.
No comment highlights available yet. Please check back later!
About Cobalt InFX on Product Hunt
“On-device transcription & summaries that know who said what”
Cobalt InFX was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #97 on the daily leaderboard. Vox Dictum is a private, on-device transcription app for macOS. Transcribe recordings, tag speakers, and generate AI summaries — 100% on your Mac. No cloud. No data collection.
Cobalt InFX was featured in Productivity (652.3k followers), Developer Tools (512.9k followers) and Artificial Intelligence (469.3k followers) on Product Hunt. Together, these topics include over 299.5k products, making this a competitive space to launch in.
Who hunted Cobalt InFX?
Cobalt InFX was hunted by Ozair. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Cobalt InFX stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Ozair
Hi Product Hunt — I'm Ozair, a programme director by trade. For twenty years I've been running large technology programmes, recording workshops, interviews, and stakeholder sessions along the way. The same problem kept coming back: I'd have hours of recordings and no practical way to turn them into usable notes without either spending an evening transcribing or uploading confidential client conversations to a cloud service.
I built Vox Dictum to fix that. It runs entirely on your Mac — no cloud, no accounts, no data leaving the device. You drop in a recording and get back a transcript with speaker names attached, plus an AI-generated summary with key decisions, action items, and topics covered. It supports 57 languages including Urdu, Arabic, and Hindi — all processed on-device.
The technical stack: WhisperKit for transcription, Pyannote for speaker diarisation, and Qwen3 for on-device summarisation, all running on Apple Silicon via MLX. The whole pipeline is local — privacy isn't a policy, it's the architecture.
The free tier is genuinely usable — unlimited transcription, speaker labelling, editing, and export. No trial, no nag screens. Pro adds larger models, AI summaries, and overlap resolution.
I'm a solo developer shipping this from London. Happy to answer any questions about the tech, the approach, or the journey.