I want to use sentiment analysis in streaming mode.

[sharp crane]

I am using streaming spreach to text. I want to analyze sentiment on streaming mode. When will we have this ability?

[north vault]

Hey there! This channel allows you to ask Kapa.ai for assistance. But it looks like you haven't connected your Discord profile to your Deepgram account yet. You can do so at https://community.deepgram.com - by doing so, you'll be able to ask questions in #1115960287183511643 if you need human assistance!

[round glade]

Hi @sharp crane. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

---

Currently, Deepgram does not support sentiment analysis for real-time or streaming audio. According to the official response in a Deepgram discussion, sentiment analysis is only available for pre-recorded audio, not for streaming transcription Deepgram Discussions.

For streaming audio, a recommended approach is to decouple the transcription and intelligence features. You can:

1. First transcribe your streaming audio using the Streaming Speech-to-Text API
2. Then use the transcribed text with the Text Intelligence API to obtain sentiment analysis results

This approach is actually recommended by Deepgram for maximizing intelligence throughput, as explained in their help center How do I maximize my intelligence throughput?. By decoupling these processes, you can achieve better scalability and reliability while conforming to rate limits.

Regarding when streaming sentiment analysis might be available, there is no specific timeline mentioned in the provided knowledge sources. If this feature is important for your use case, I'd recommend joining Deepgram's Discord channel (https://dpgr.am/discord) where they keep the community updated on new releases and feature announcements.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: