I'm a reseller and consultant, and I mainly use Deepgram as an AI voice integration service.

When I use Vapi AI to implement voice AI call solutions, the understanding of German in Nova 2 feels more reliable than the last version. This observation was from approximately two months ago when I used it.

I use Deepgram for voice integration when I have a customer getting voice calls, implementing solutions with AI. I use it for calling agents, cold calling agents, and mostly for speech to text. I always use it to transcribe the voice to LLM text streams. I also used it for a platform with web integration, allowing customers to schedule calls with AI coaches on different topics, where I did the transcription with Deepgram API integration into LiveKit so the system could understand what the customer is saying.

I started with Vapi AI, which introduced me to Deepgram. Now I have a private account there for other solutions than Vapi. Initially, Deepgram was the only reliable service for my needs, which is why I have always used it and never switched. I stick with Deepgram because it consistently works; I have no reason to test something else that might not be as effective.

The most important feature of Deepgram for me is the transcription service, along with the reliability of the service. If you integrate a service and it does not respond or has delays, if it's not reliable, it doesn't matter if it's high quality; it has to work every day so that my customers are always happy and not offended because nothing is working at times.

Deepgram's low latency transcription has greatly impacted my ability to deliver reliable voice agents and provided very good transcription. I showcased this on my website, allowing someone to call and have real-time transcription displayed, which was very beneficial. I didn't find a good service a year ago that could perform this, and without Deepgram, I probably wouldn't have sold any AI automation services.

Deepgram is very reliable for normal conversation, but when it comes to special names or information, I'm not entirely sure how to implement it perfectly. I did use a feature to highlight special words based on the topic, but I've seen overweighting of this topic, where normal words weren't recognized properly.

The handling of different topics needs to be optimized to be more accurate. I could upload lists with special words for specific topics. In my experience, it was not perfect, as there were only a few words that were understood properly. When I had an AI interview for coding, Deepgram didn't capture the names of programming languages or well-known LLMs accurately all the time. For example, when a person said "I'm experienced in Python development," Deepgram didn't get the word Python correctly.

When Deepgram Nova 3 was released, I experienced problems with the API, but it could be on the Vapi side; I'm not sure, which is why I stick with version two, but I think currently there is no problem anymore.

The setup could be easier, as everything is moving towards no-code solutions. You can configure everything properly on the dashboard and get a JSON file with the structured output to insert into other programs. If there were a way to configure special words for the API more readily, that would be helpful.

The initial setup needs to be optimized to be more intuitive.

I have been working with Deepgram for a bit over a year.

Deepgram always matched the workload, so I didn't have any performance issues.

Deepgram always matched the workload, so I didn't have any performance issues. In Germany, we face GDPR issues, which is annoying. We have to ensure services remain within EU borders. I'm not sure if Deepgram offers options to choose the server location, such as having a server in Frankfurt like AWS.

I haven't communicated with Deepgram's technical support at all. Until now, I've always found the documentation sufficient and managed without needing support.

The documentation is fine. Most of the time, I use AI to read it and implement directly. If my programming assistant can't find the information in the documentation, I go in and read it myself, pointing out specific topics for the AI to understand how to implement features. For me, the most important aspect of the documentation is that it is structured so that AI can read it effectively.

I started with Vapi AI, which introduced me to Deepgram. Now I have a private account there for other solutions than Vapi. Initially, Deepgram was the only reliable service for my needs, which is why I have always used it and never switched. I stick with Deepgram because it consistently works; I have no reason to test something else that might not be as effective.

The setup could be easier, as everything is moving towards no-code solutions. You can configure everything properly on the dashboard and get a JSON file with the structured output to insert into other programs. If there were a way to configure special words for the API more readily, that would be helpful.

The initial setup needs to be optimized to be more intuitive.

I've seen a return on investment with Deepgram. Last week, I sold an agent for 2,500 and included Deepgram in the configuration. The customer had tested different solutions and found them inadequate. I hosted a demo service for my agent using Deepgram, and the customer tested it through a link on my landing page. He stated that the performance was significantly higher than elsewhere, and he found it suitable for his needs. Deepgram is part of it, contributing to my revenue.

If the handling of the German language improves continuously, it would be beneficial for me.

I always use Krisp or something similar as a second service to filter out background noise, but I haven't checked if different languages or speakers are detected properly.

On a scale of 1-10, I would rate Deepgram a 9.

I use Deepgram for audio transcriptions and speech recognition. I am working on a feedback survey app where users provide verbal feedback that Deepgram transcribes into text.

We receive the results and implement features like punctuation and Smart Format.

Deepgram has significantly improved our transcription process in terms of speed and accuracy. It has allowed us to efficiently convert verbal feedback into text, enabling quicker analysis and implementation of new features.

Integrating Deepgram has streamlined our workflow, enhancing productivity and delivering more accurate transcription results.

We previously used IBM Watson, which was slow and had limitations in accurately transcribing words. After evaluating OpenAI's Whisper model, we discovered Deepgram, which incorporates Whisper and adds the powerful Nova model.

Deepgram's latency is impressively low, around 0.5 to 1 second, making it a superior choice.

Live transcription could be improved. Sometimes, Deepgram's WebSocket is disposed of due to redundancy issues. Enhanced stability in live transcription would be beneficial.

I have been using Deepgram for one and a half years.

Initially, we encountered some stability issues, but Deepgram has since improved its architecture. With the addition of hooks for status updates, the accuracy has improved to approximately 90 to 95%, which is better than other models we've tested.

It's scalable. Our platform handles 50 to 60 users simultaneously without compromising accuracy. For instance, a 20-minute audio file was transcribed within a second, demonstrating its ability to handle large volumes of audio data effectively.

My experience with customer service and support has been positive. They are responsive and helpful, and they provide timely resolutions to any issues.

We previously used IBM Watson, but it didn't deliver appropriate results. We searched for alternatives and found OpenAI's Whisper model, which was initially slow. After thorough analysis, we discovered Deepgram. It proved to be superior, leading to our decision to migrate. We used a detailed spreadsheet to compare various models before making the switch.

Thanks to clear documentation, the initial setup was very easy. If you have prerequisite knowledge of the programming language you're using, it’s straightforward to follow the documentation and implement it into your system. When I started, I closely followed the documentation, which made the process very manageable.

Deployment model: We last deployed it on the Google Cloud Platform (GCP).

The implementation was done in-house.

Our ROI has increased due to enhanced transcription accuracy and speed, leading to more efficient workflows and better user satisfaction.

The pricing is moderate. While live transcription may incur some charges when the connection is open, they become minimal over time. So, it's a balanced option—neither cheap nor overly expensive.

Yes, besides IBM Watson, we evaluated OpenAI's Whisper model.

Deepgram is highly recommended. Users don’t need to do anything special before using it, as the documentation is comprehensive. I am a Node.js developer and have used Deepgram packages for Node.js. Understanding your programming language is key, whether it's Node.js, Python, or others.

AI Features:

I have integrated various AI models into our application. Deepgram's sentiment analysis feature allows us to create graphs and analyses to determine if words are positive, negative, or neutral. This helps us summarize feedback and derive actionable insights.

My ratings:

I would rate it an eight out of ten. The live transcription feature needs improvement as the WebSocket sometimes gives errors or breaks down during live streams.

We use the solution for TTS (Text-to-Speech) and STT (Speech-to-Text) purposes.

The solution's Speech-to-Text conversion feature is really awesome.

Deepgram is currently restricted to only the English variants, but it should include other languages, such as German or French.

I have been using Deepgram for five to six months.

Deepgram is a stable solution.

The Deepgram cloud can handle large volumes of audio data. Around three to four people use the solution in our organization.

The solution’s initial setup is easy.

Deepgram is a cheap solution. We can create an account for $200, which we can initially use for the Deepgram services.

I have used Deepgram with Twilio for the calling system. I would recommend Deepgram to users who want to use it for speech-to-text purposes.

Overall, I rate the solution an eight out of ten.

I am the software development team lead in my company, and we are creating a speech recognition product based on a few different engines. The company works in the legal process, so my team generates a machine-based transcript and then converts it to a readable format. It saves time for the person using the machine-based transcript as a starting point.

The solution's most valuable feature is its speed of transcription. It is one of the fastest tools, especially if you compare it to the second fastest solution that you can get, which is 20 times faster. Thus, it is not just a marginally faster product.

In comparison to Deepgram, I would say that the transcript accuracy offered by other products is much higher. In our company, we had five jobs, and each job was generated by two different engines. One of the aforementioned engines was Deepgram, and the transcribers had two versions, and the users didn't know which one was which version. After the aforementioned process was carried out, the users had to choose which version they thought was less work to convert to the final or the perfect legally binding document since the tool was getting paid per page. Deepgram had a clear incentive to do some little work as fast as possible and to get a particular amount of money. In our company, we didn't have a huge sample size because we are a small company. We did five jobs with five different transcribers, and each job had two versions. A blind test was done, and we found that the other tools were marginally more accurate than Deepgram.

I would like it to be more accurate. I can get maintainability and faster transcripts with the perfect features with an improved tool.

I have been using Deepgram for a year. I use the solution's latest version. I am an end-user of the tool.

I don't use all of the features in the tool because Deepgram adds new features every few months. The features that I have been using in the tool have been very stable. I have never had any issues with the tool and it has never crashed. In our company, we just update to the latest version, and see if there are no issues until the next update.

I use the tool as a software developer and transcriber. Though I don't know the number of transcribers that work in our company , I can say that it runs into hundreds.

I contacted the solution's technical support for help, and I got a nice, decent service and had no complaints at all. At the moment, whenever you want to update Deepgram by yourself, it is a very easy process. You just get the version of the tool and pull it from Docker. If you want to update the model, you have to contact the support anyway. I haven't contacted the support team very often. I might have contacted the product's support team three times just to update the new versions of the model. I got decent support from the tool's support team.

My company still uses multiple products in parallel to Deepgram. For example, in transcript-related business, some clients want to get the transcript super fast or in a few hours. You need to produce the machine transcript in a few minutes and give it to the transcriber, who should start working immediately on it. In such cases, there is a huge improvement when one uses Deepgram, which is a major advantage.

If I consider and compare the other engines I have used with Deepgram, I would say that the ease of installation is one of the strong points of the product. Compared to all other engines, the installation of Deepgram has been simpler and far more stable. It just gets updated, and it runs properly. The good thing is that the tool is modular. In the tool, the modules and the engine itself are separate objects. If you want to update only the module, then there is no need to redeploy anything since most other engines that we have in our company are on an on-premises model.

The solution is deployed on on-premises and cloud environments. It is deployed in the private section of our company's cloud. We aren't using the API and prefer to use our own deployment.

When using Deepgram, one needs to pay for the hours or minutes for which the transcription is needed. The more hours you commit to in advance, the cheaper the price. It is slightly cheaper than the other engines we used. You should take into account that you usually pay for cloud resources or even if you are doing just an on-premises deployment, and since it is a fast process, theoretically, you can save twice, like, once on the money you pay for usage and the second time you pay for cloud resources because if you can, like, finish transcribing in a minute instead of an hour, you can know, if your pipeline scales down, you will only pay for that minute.

Whether you should use the tool or not depends on your use cases and the main use cases where it is used. Based on the engines and factors like maintainability or how easy it is to maintain, and if you consider them to be your priorities, you definitely go with Deepgram.

Speaking about how Deepgram handles large volumes of audio data without compromising inaccuracy, it is always a trade-off. As I said, Deepgram is not as accurate as the other engines we're using, but the difference is marginal, and if speed is more important to you, you should go with Deepgram. I think if the accuracy of the transcript is far more important, other engines give better results.

For an end user, the tool offers on-premises deployment, and it also has an API. Using API is super easy since you just log in to the site and create an account, and you can start using it. If you want to deploy it on an on-premises model, you need to have a basic understanding of the cloud and how it works. The tool has a step-by-step guide on its website, which is very nice, and I still use it even because it is super simple and can be easily understood.

We haven't actually used our AI features at the moment because we're not quite sure how we can use them in our company because we are working on the legal transcript, and those have to be developed word by word even if the person who speaks, says certain things incorrectly. We have to maintain 100 percent accuracy. I am not sure how we can apply AI features in the tool, but we are always looking at the AI aspect in our company.

Deepgram offers some clear advantages over other applications. If you want a tool that produces transcripts in a very fast manner, there is nothing that comes even close to being disputed with Deepgram.

I rate the tool an eight or nine out of ten.