Recommendation on using Nova-3 Multilingual for individual languages

[ylvanorrby]

Hi Deepgram team! 👋

I noticed in your documentation that the new Nova-3 model now supports multiple languages through the Multilingual version, which is very exciting!

I’m wondering if you recommend using Nova-3 Multilingual also for transcription of individual languages such as German, French, or Spanish — or if Nova-2 is still preferred for those languages (at least until dedicated Nova-3 models for them become available)?

In other words: Is Nova-3 currently best suited only for English and truly multilingual audio, or is it also your recommended choice for monolingual content in supported languages?

Additionally, I’m curious if keyterm prompting is supported in the multilingual setting, or if it currently works best (or only) with English?

Thanks in advance for the clarification — and for a great API!

Best regards,
Ylva

[deepgram-community[bot]]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
_{Consider joining our Discord community for more opportunity to engage with your fellow Deepgram users. You can earn points which can be redeemed for cool stuff by being active in our communities!}

[deepgram-community[bot]]

Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion.

[deepgram-community[bot]]

It looks like we're missing some important information to help debug your issue. Would you mind providing us with the following details in a reply?

• The programming language you are working in (e.g. JavaScript, Python).
• The deepgram product you are using (e.g Speech to Text, Agent API)
• A request ID that triggered your error or issue.

[deepgram-community[bot]]

We always recommend you do some testing / bench marking to see what works best for your specific audio and use cases.

But In our Docs we say:

https://developers.deepgram.com/docs/models-languages-overview

• nova-3: Recommended for most use cases, especially audio with multiple languages, background noise, crosstalk and far field audio
• nova-2: Recommended for use cases with non-English transcription, and filler word identification.
So I'd assume if you have a single language to process, using Nova-2 might be better than using a multi-lingual model with Nova-3 to do that processing.

Currently Key Terms are only available on Nova-3 for English

https://developers.deepgram.com/docs/keyterm

This message was sent by John Vajda from Deepgram, via our community automation.

[anotine10]

Hi, is this still the case now?