Deepgram's latest STT updates and what Telli.sh users get next
Deepgram added live Listen reconfiguration, Korean spacing fixes, multilingual numerals, and stronger batch diarization. Because Telli.sh uses Deepgram as its default speech engine, these updates matter for live AI notes.
Deepgram has shipped several speech-to-text updates that are directly relevant to real-time meeting notes. We reviewed the official Deepgram changelog on June 28, 2026, and the direction is clear: speech recognition is becoming more adaptive, more multilingual, and more useful for long conversations.
That matters for Telli.sh because Deepgram is our default speech engine in production. When the engine improves, the foundation of live notes, uploaded audio, summaries, and multilingual meeting records improves with it.
Image: Dejan Krsmanovic, Wikimedia Commons, CC BY 2.0.
What Deepgram announced
The newest changelog item is UpdateListen, announced on June 15, 2026. It lets a live voice session adjust Listen configuration during a conversation without restarting the session. The tunable fields include end-of-turn thresholds, hard timeout, keyterms, and language hints.
For users, this points to a better live-note experience: meetings can adapt when the topic, vocabulary, or language mix changes instead of forcing a restart.
Deepgram also announced several STT improvements in May:
- Korean transcripts now have improved word spacing for
koandko-KR, which should make Korean notes easier to read and review. - Profanity filtering is now supported across multilingual Nova-2, Nova-3, and Flux models using
language=multi. - Nova-3 multilingual can format spoken numbers as digits for many supported languages, which is useful for budgets, dates, counts, and action items.
- Batch speaker diarization v2 is available through
diarize_model; Deepgram reported that v2 was preferred 3.3x over the prior production diarizer in side-by-side human evaluation, with the largest gains on contact-center audio.
There is one important limitation: Deepgram says diarize_model is for batch requests, not streaming. We will treat that distinction carefully in Telli.sh rather than presenting every provider feature as an immediate live-session change.
What this means for Telli.sh users
The most immediate benefit is transcript quality. Korean users should see more readable raw transcripts as Deepgram's spacing fix reaches model-side output. Multilingual meetings should benefit from stronger number formatting and broader moderation controls.
The next layer is session control. UpdateListen is especially relevant to live AI notes because meetings are rarely static. A technical review may need boosted product terms. A bilingual call may need language hints. A fast conversation may need different turn timing. These controls give us a cleaner path to make Telli.sh live sessions more responsive without interrupting the recording.
For uploaded recordings and longer batch workflows, diarization v2 gives us another quality lever for speaker-aware notes. We will validate it on representative meeting audio before routing production traffic to a new diarization mode.
Better STT still needs a product layer
Deepgram improves the transcript. Telli.sh turns the transcript into a workflow: live recording state, source language selection, reviewable text, AI refinement, summaries, decisions, action items, and reusable meeting records.
That is the user-facing improvement we care about. Better speech recognition should not mean more settings for users to manage. It should mean fewer broken transcripts, clearer notes, and less work after the meeting ends.
