Reviews from AWS Marketplace
0 AWS reviews
-
5 star0
-
4 star0
-
3 star0
-
2 star0
-
1 star0
External reviews
External reviews are not included in the AWS star rating for the product.
They are going to be a core pillar of the enterprise voice market
What do you like best about the product?
Its cheaper than any other service at scale, and you can fine tune your own models to your liking.
What do you dislike about the product?
They're still not as asvanced in as many languages as google
What problems is the product solving and how is that benefiting you?
Better ASR, at a better cost
- Leave a Comment |
- Mark review as helpful
Affordable, Accurate Call transcription
What do you like best about the product?
The integration with our platform was very straightforward. We were able to add Deepgram as an additional transctipion engine in a couple of days, and compare results to other vendors. The results were comparable, and the price is significantly better than others in the market. Results also come back from the cloud service very quickly. There is also a lot of flexibility with the ability to run onprem or in the cloud, and the cost offset for onprem compute is appreciated.
What do you dislike about the product?
The diarization feature is still not as mature as it could be. It hit maybe 70% accuracy in identifying speakers, although this is comparable to other solutions that we've evaluated.
What problems is the product solving and how is that benefiting you?
We're using deepgram for contact center call transcription at scale. The transcript quality is on par with other providers, but the speed and cost are both greatly improved.
Recommendations to others considering the product:
They are very amenable to a trial setup, and integration was straightforward, so the barrier to entry is low. Their feature set is limited to transcription at the moment, but they say an expanded feature list including things like sentiment analysis is coming soon. If speech to text is the primary use case though, Deepgram seems like an innovative and capable vendor.
Speech recognition
What do you like best about the product?
İ can easily and accurately phonetic search. The engine is quite correct that can grasp everything when it is being said. In our sales process, it is used for the phone sales and manages the process by implementing smart features it covers as phonetic search appears, and also audio transciption is another great aspect of the software that these features have greatly contributed to the sales of our company. It provides the service for MAC desktop version since its rival in the market could not manage to provide the same service.
What do you dislike about the product?
I could not see the chat function that is crucial these days that the communication between vendor and customer should be interconnected and tight. Lack of training features could be a disadvantageous factor so far.
What problems is the product solving and how is that benefiting you?
It helps us in our sales process that we usually communicate with foreign customers and it transcripts the audio, it is connected phonetic search system that enhances the sales process a lot.
Voice transcript that the records the moments by extracting the background noise in the transcript
What do you like best about the product?
The software works precisely that what the system records is pretty accurate that led to having the high quality work. The interface is the pretty handful that it did not take much time to get to know the systems and the features lie behind the buttons. The accelerated process in transcription hugely enhances our work that it takes the right information by bypassing the unwanted noise in the record. I used it for my Podcast that it easily take all the useful information rightly that I did not see the need to use additional equipment.
What do you dislike about the product?
To be honest there few things to say about the negative aspects of the software because the system can provide everything we need to implement our tasks, however, the latency that happens when I change the pages within the software is heartbreaking.
What problems is the product solving and how is that benefiting you?
We have the meetings with the customers that the need for taking notes, the recording appears as the critical issue the enhancement of the sales process turns into the heavy dependence on the software to archive the important information.
Recommendations to others considering the product:
Take into consideration that the program removes the world burden in the sales sector.
A powerful speech recognition engine
What do you like best about the product?
- The accuracy of the tool to generate transcripts of audios with even poor quality
- Speed of transcripts generation
-It can understand all types of audios be it podcasts,music , sales calls etc.
-It identifies specific words from the audio accurately
- Speed of transcripts generation
-It can understand all types of audios be it podcasts,music , sales calls etc.
-It identifies specific words from the audio accurately
What do you dislike about the product?
There is no such thing I dislike. The only thing I can recommend is to work of improving the accuracy further.
What problems is the product solving and how is that benefiting you?
Making notes from Sales calls, recorded meetings , training etc.
Using the transcript for quality training
Using the transcript for quality training
Deepgram Partnership
What do you like best about the product?
Our business in data annotation and language services does not have a standard model for all projects so we're constantly looking for extensions to existing AI models to achieve results. One example was a requirement to do automated time stamping per word in Japanese. Deepgram continually upgraded their models throughout the project to support us.
What do you dislike about the product?
I honestly have nothing to say here. There's nothing that I dislike.
What problems is the product solving and how is that benefiting you?
We have requirements from customers that their data may not leave our domain so Deepgram has provide us and on prem solution.
For key customers with on-going projects Deepgram provides custom model training that tunes specifically for that customer's audio.
For key customers with on-going projects Deepgram provides custom model training that tunes specifically for that customer's audio.
Recommendations to others considering the product:
Deepgram's approach to Automated Speech Recognition is unique in the industry in that they train models for each discrete customer which provides more accurate results than a general model.
The team is very easy to work with; near zero latency in their response to questions and offer very attractive pricing.
The team is very easy to work with; near zero latency in their response to questions and offer very attractive pricing.
Phenomenal Transcription Engine with Incredible Support and Robust API!
What do you like best about the product?
- Accurate Transcripts
- Diarization
- Speed to Return Transcript
- Able to Pull Various File Types
- Diarization
- Speed to Return Transcript
- Able to Pull Various File Types
What do you dislike about the product?
- Sometimes its difficult to get custom features built out
What problems is the product solving and how is that benefiting you?
Call Center Quality Monitoring at Scale using Speech Analytics. We use Deepgram as our Speech-to-Text Engine in several ways.
One way is to enable Call Criteria to handle large contact center volume and use AI to identify the calls that our predictive engine has analyzed as having a potential violation. Then, we use our human quality control analysts to get a much deeper, more thorough picture of the recording to accurate pinpoint and timestamp what happened and where.
More often than not, there are also a lot of false positives and false negatives surrounding speech analytics. We use humans to accuracy check these so we're eliminating these false negatives/positives altogether. Who would want dirty data? Why settle for data that may have that kind of falsities? How can you apply anything programatic to something that isn't accurate? That's why we use humans to verify if the speech analytics flags were accurate or not.
One way is to enable Call Criteria to handle large contact center volume and use AI to identify the calls that our predictive engine has analyzed as having a potential violation. Then, we use our human quality control analysts to get a much deeper, more thorough picture of the recording to accurate pinpoint and timestamp what happened and where.
More often than not, there are also a lot of false positives and false negatives surrounding speech analytics. We use humans to accuracy check these so we're eliminating these false negatives/positives altogether. Who would want dirty data? Why settle for data that may have that kind of falsities? How can you apply anything programatic to something that isn't accurate? That's why we use humans to verify if the speech analytics flags were accurate or not.
Great Transcription/Diarisation Partner
What do you like best about the product?
Deepgram is a reliable partner for our company in providing critical transcription/diarisation of customer sales calls. Fast turnaround and always improving accuracy
What do you dislike about the product?
Like anything - accuracy of transcription is always something we are striving to improve on. It would be great if the accuracy curve sped up
What problems is the product solving and how is that benefiting you?
Call transcription and diarisation as part of our conversation intelligence and sales coaching technology.
showing 191 - 198