Universal 2 addresses the part that makes transcripts actually usable: getting names, numbers, and formatting right automatically. The 24% improvement in proper noun recognition and 21% gain on numerical data are not just benchmark wins - they translate directly into transcripts that need significantly less manual cleanup.
What stands out is the formatting layer. Handling punctuation, casing, email addresses, and monetary amounts consistently means the output is ready to work with immediately, not just technically correct. For anyone processing call recordings, meeting transcripts, or interview audio at any volume, that reduction in editing time compounds quickly.
The free tier makes it straightforward to evaluate before scaling, which is the right approach for a tool that lives or dies by how it performs on your specific data.
We also reviewed Universal 2 on our platform https://www.producthunt.com/products/completeaitraining-com — where we list and categorize 7,000+ AI tools for different jobs and skills.
AssemblyAI
Kai
@iharnoor Exactly what I was looking for, ahah, I was looking for a base to play around with Claude Code and build an ultra-personalized tool ;)
Dial
giving away the actual reference implementation instead of just docs is the part I like here. we build on top of streaming STT for a calling product and the gap between "the API works in a curl example" and "here's how audio actually gets captured, chunked and streamed in a real app" is usually where the time goes. one thing worth asking: does Blurt handle the awkward middle of a hold-to-talk session, someone pausing mid-thought for a few seconds, without either cutting the stream early or drifting out of sync with what's still being typed?