About Deepgram
Deepgram Features
- Voice-Activity Detection (VAD) : Assists in identifying the presence of human speech in the audio file.
- Interim Results : Helps in monitoring and providing the transcripts while the audio is streaming.
- Summarization : Summarizes the complete content of audio files and returns them into the JSON response.
- Topic Detection : Identifies and generates key points of the content in the audio provided.
- Smart Format : Assists in adding extra formats to the transcript to improve readability.
- Find and Replace : Makes appropriate changes in the terms or phrases in the transcripts if necessary.
Deepgram Ratings and Reviews
- Vatsal F.Small-Business(50 or fewer emp.)
Deepgram has been one of the best speech to text ecosystems for us. We have used almost all the models but Deepgrams stands out due to eas of integration, support for propeirotry as well as open source models (Whisper) and a great dashboard that allows us to track our usage transperantly. Review collected by and hosted on G2.com.
- Verified User in Information Technology and ServicesSmall-Business(50 or fewer emp.)
What I don't like about Deepgram is the difficulty in handling a large quantity of audio when the language is different from English. Some transcriptions couldn't be generated, and the audio quality with which I built an application wasn't the best. There are other alternatives that provided better transcriptions. Additionally, when I tried to contact the support team to see if there was any solution to this problem, I never received a response. The margin of error wasn't too high compared to the volume of audio we were processing, but for our use case, precision was necessary. Review collected by and hosted on G2.com.