Deepgram just released Nova-3 (real-time multilingual speech-to-text) - beta access?
Just received an email about Nova-3. Looks really interesting. We have been playing around with real-time language switching on our phone calls. Looks like Nova-3 would support way more languages beyond just English and Spanish. Could be a game changer. Hoping to get beta access to the API soon.
187 views
Replies
Product Hunt
Oh interesting, so @ankitgordhandas your voice agent switches languages while on a call? Like it asks users what language then switches?
Intersect Labs
@ankitgordhandas @rajiv_ayyangar even better! If the person on the other end starts responding in Spanish, it switches to Spanish.
Just gave Deepgram a spin and wpw Feels like the voice AI equivalent of having super-hearing. Transcription is crazy fast and impressively sharp even picked up my half-mumbled test phrases
Loving how dev-friendly it is, but now I’m wondering how well does it hold up with accents or background noise? Like, would it survive a loud coffee shop or a Zoom call with three people talking at once?
Anyone tried throwing it into the chaos yet?
How does Flux handle overlapping speech in multi-party calls? The ~260ms end-of-turn detection is fast enough for 1:1 voice agents, but conference-style crosstalk is where most STT pipelines still fall apart. Self-serve vocab customization on Nova-3 without retraining is a smart call for teams that can't wait on fine-tuning cycles.