[Nova 3] Ability to add context to an audio file to improve WER

[phin]

Originally posted here: deepgram/deepgram-js-sdk#433

Proposed changes

Provide a detailed description of the change or addition you are proposing

Context

I have a feature request for Nova 3, not sure where I should send it over:

We found great improvements to word/sentence detection by adding context to the audio file. Example, the previous conversation, or notes about the topic discussed.
We found this in Whisper and Qwen and as a language learning platform, it helps detect discussions with strong accents better (think Duolingo, Usefluently etc)

I am making a comparison on our dataset between Google, Nova, vs. Whisper/Qwen with context.

This may have more impact than fine tuning!

Why is this change important to you? How would you use it? How can it benefit other users?

People with strong accents, learners of a new language, have trouble being understood by LLMs. By adding the context/topic of the conversation, it could narrow down the set of words to detect, like a human would.
We are looking to train models directly with a dataset of users from another language practicing French, but we think we can get a better return on investment by just adding it as context to the LLM.
See Qwen - https://huggingface.co/spaces/Qwen/Qwen3-ASR-Demo

Possible Implementation

Not obligatory, but suggest an idea for implementing addition or change

Pass via the API a new param "context", see Qwen here - https://huggingface.co/spaces/Qwen/Qwen3-ASR-Demo

Other information

Anything else we should know? (e.g. detailed explanation, related issues, links for us to have context, eg. stack overflow, codepen, etc)

[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 deepgram product you are using (e.g Speech to Text, Agent API)
• A request ID that triggered your error or issue.