How to enable/activate ML feature's?

[aleem11]

The parameters for sentiment, intent, and topic detection are not working for me. The Deepgram logs indicate that these parameters are not enabled for my account. How can I get these activated? @michaeljolley @jcdyer

[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.

[aleem11]

Programming language: The script is written in JavaScript.
Deepgram product: The script uses the Deepgram Live Transcription API for Speech to Text.

[jkroll-deepgram]

Hi @aleem11, can you please share your Deepgram project ID? If you log into the Deepgram Console, you'll see it listed at the top (and in the URL itself): like "Project ID: 00000000-0000-0000-0000-000000000000"

[aleem11]

My Deepgram project id from the console is: 7f1bb92e-2fe1-482e-bcba-19c2a542d9d5

…

On Mon, Nov 25, 2024 at 8:18 PM Julia Kroll ***@***.***> wrote: Hi @aleem11 <https://github.com/aleem11>, can you please share your Deepgram project ID? If you log into the Deepgram Console, you'll see it listed at the top (and in the URL itself): like "Project ID: 00000000-0000-0000-0000-000000000000" — Reply to this email directly, view it on GitHub <#1009 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ASSUEIEZ6VE2YC53YFQSKX32CM5TDAVCNFSM6AAAAABSLMSISKVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMZXGM4TCNA> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[jkroll-deepgram]

Hi @aleem11, thanks for sharing your project ID.

I don't see any permissions gating access to the ML (audio intelligence) features for your project.

If you see any errors when using them, can you please share the Deepgram request IDs and error messages?

Do note that these features are only available for English pre-recorded transcription, so you would see errors if requesting them on streaming transcription or non-English transcription.

[aleem11]

Thank you for your response. I tested the Deepgram sentiment feature again with my project and confirmed that the sentiment feature is enabled. However, I am not receiving sentiment data in the response, even though I have included sentiment=true in my script. To assist in troubleshooting, you can verify this in the last log data using the following details: - *Request ID:* 3bd952f5-729d-42df-afa3-5653133ee8de - *Project ID:* 7f1bb92e-2fe1-482e-bcba-19c2a542d9d5 *Below is the complete response I received during my last test:* json { "type": "Results", "channel_index": [0, 1], "duration": 3.9499998, "start": 4.37, "is_final": true, "speech_final": false, "channel": { "alternatives": [ { "transcript": "Hi, Krishna. Alim speaking here.", "confidence": 0.97314453, "words": [ { "word": "hi", "start": 6.13, "end": 6.37, "confidence": 0.99365234, "speaker": 0, "punctuated_word": "Hi," }, { "word": "krishna", "start": 6.37, "end": 6.87, "confidence": 0.97314453, "speaker": 0, "punctuated_word": "Krishna." }, { "word": "alim", "start": 7.0099998, "end": 7.17, "confidence": 0.87475586, "speaker": 0, "punctuated_word": "Alim" }, { "word": "speaking", "start": 7.17, "end": 7.67, "confidence": 0.9951172, "speaker": 0, "punctuated_word": "speaking" }, { "word": "here", "start": 7.8099995, "end": 8.309999, "confidence": 0.94189453, "speaker": 0, "punctuated_word": "here." } ] } ] }, "metadata": { "request_id": "3bd952f5-729d-42df-afa3-5653133ee8de", "model_info": { "name": "2-general-nova", "version": "2024-01-18.26916", "arch": "nova-2" }, "model_uuid": "c0d1a568-ce81-4fea-97e7-bd45cb1fdf3c" }, "from_finalize": false} *My code Snippet: * const params = { model: 'nova-2', language: 'en', smart_format: true, punctuate: true, paragraphs: true, diarize: true, sentiment: true, encoding: "mulaw", // Example encoding sample_rate: 8000, // Example sample rate }; // Construct URL with parameters const urlParams = new URLSearchParams(params).toString(); const deepgramUrl = `wss://api.deepgram.com/v1/listen?${urlParams}`;

…

On Tue, Nov 26, 2024 at 10:48 PM Julia Kroll ***@***.***> wrote: Hi @aleem11 <https://github.com/aleem11>, thanks for sharing your project ID. I don't see any permissions gating access to the ML (audio intelligence) features for your project. If you see any errors when using them, can you please share the Deepgram request IDs and error messages? Do note that these features are only available for pre-recorded transcription, so you would see errors if requesting them on streaming transcription. — Reply to this email directly, view it on GitHub <#1009 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ASSUEIF2JV5MVE5Q7TF3FDD2CSYAHAVCNFSM6AAAAABSLMSISKVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMZYGY2TGNY> . You are receiving this because you were mentioned.Message ID: ***@***.***>

[jkroll-deepgram]

Hi @aleem11, note that sentiment and other ML features are only available for pre-recorded transcription. You're using live streaming transcription.

If you want to record your audio and then submit it to our audio intelligence REST API, or use streaming transcription and then send the text transcript to our text intelligence endpoint, then you can get the sentiment information.