Skip to main content

Nova-3 Improved Models for Danish, Estonian, Flemish, Italian, Lithuanian, Macedonian, Polish, Urdu, and Vietnamese

By Steven Van ·

Nine Nova-3 language models get quality updates for batch or streaming transcription, live now with no API changes required.

Deepgram has updated its Nova-3 monolingual speech-to-text models for nine languages, improving transcription quality for batch and streaming workloads. The improvements cover:

  • Batch and streaming: Polish (pl), Danish (da)
  • Batch only: Vietnamese (vi), Flemish (nl-BE)
  • Streaming only: Estonian (et), Macedonian (mk), Urdu (ur), Italian (it), Lithuanian (lt)

No API request changes are needed: the updates are live for all users on the existing model names. Self-hosted customers need to request the updated models from their Deepgram account representative.

Deepgram
Deepgram
Power enterprise voice solutions with Deepgram’s Speech-to-Text, Text-to-Speech, and Voice Agent APIs. Real-time, accurate, and built for scale.
View Deepgram →

Read the original announcement →

Read Nova-3 Improved Models for Danish, Estonian, Flemish, Italian, Lithuanian, Macedonian, Polish, Urdu, and Vietnamese on Creators Toolbox