Noise Removal

[atomic junco]

Does deepgram have noise removal for speech to text

[spring bay]

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

---

Yes, Deepgram does have noise reduction capabilities for speech-to-text transcription. According to the Migrating From Google Speech-to-Text (STT) to Deepgram documentation, Deepgram offers noise reduction as one of its features.

However, it's important to note that Deepgram's approach to handling noise is somewhat unique. As mentioned in a GitHub discussion about noise suppression, Deepgram doesn't apply noise suppression to the audio they train on. This allows their models to more accurately handle audio that contains background noise.

While Deepgram does have built-in noise reduction capabilities, they don't actively suppress noise in the same way some other services might. Instead, their models are trained to be robust to noisy environments, which can lead to better transcription accuracy in real-world scenarios with background noise.

If you need additional noise suppression beyond what Deepgram provides, the same GitHub discussion suggests considering open-source solutions like noise-suppression-for-voice, free services like utterly, or commercial solutions like krisp.ai. However, it's worth noting that applying too much noise suppression before sending audio to Deepgram might actually worsen transcription quality in some cases.

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