Hello!
Is it possible to identify the clapping sound on an audio together with the speech? I want to identify when a single talk is over on a long session with multiple speakers.
#Is it possible to identify the clapping sound?
spark mango
errant spokeBOT
Hi @spark mango. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
Hmm, I don't know enough to give you a confident answer yet. The knowledge sources provided do not contain specific information about Deepgram's ability to identify specific non-speech sounds like clapping in an audio file.
However, Deepgram does have a feature called End of Speech Detection, which uses a Voice Activity Detector (VAD) to gauge the tonal nuances of human speech and differentiate between silent and non-silent audio. This might be useful in identifying when a speaker has finished speaking, but it's not clear if it can detect specific sounds like clapping.
You may need to determine what constitutes "end of speech" for your specific use case. For example, if a clap signifies the end of a talk, you might need a different kind of audio analysis tool that can identify that specific sound.
For more information, you can refer to the Deepgram Documentation (https://developers.deepgram.com/docs/understanding-end-of-speech-detection).
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
spark mango
@errant spoke so it's not possible to create a closed caption for any environment noise. Correct?
errant spokeBOT
Let me check the knowledge base for you. One moment! :books:
Correct, based on the provided knowledge sources, Deepgram's primary function is to transcribe speech. It does not specifically mention the ability to transcribe or identify environmental noises such as clapping or other background sounds.
Deepgram's transcription service is designed to handle audio that has background noise, but it does not specifically transcribe or identify that noise. It focuses on the speech content of the audio.
For creating captions, Deepgram provides functionality to generate WebVTT and SRT captions for an audio file, but this is primarily for the spoken content. You can refer to the Deepgram Documentation (https://developers.deepgram.com/docs/automatically-generating-webvtt-and-srt-captions) for more details on this.