Easy to set up and get first API response with helpful docs and UI. The Nova-3 AI model's error rate is low and split utterances with timestamps out-of-the-box is nice. Pricing is great and the free $200 credit to start is incredible. Review collected by and hosted on G2.com.

Although Nova-3 error rate is low, it does struggle compared to other ASR models, particularly with British accent. I will be keeping an eye on new model releases with lower WER. Review collected by and hosted on G2.com.

I love that Deepgram's API is super easy to set up in just a couple of minutes. I never even go into the UI because the API alone is great. The instant transcription is quick, reliable, and quite accurate, which is essential for my freight brokerage, where we need to call truckers all the time. The fact that it works better than our phone system provider is a big plus. I honestly don't spend any time on it, which is the biggest compliment I could give since it just works. Also, the setup process couldn't be easier—I'd give it a nine out of ten. All I had to do was plug the API key into Claude Code and the whole thing set itself up. Their documentation is really good too. Review collected by and hosted on G2.com.

Honestly no complaints Review collected by and hosted on G2.com.

I appreciate Deepgram as a developer-first platform and use it for streaming audio. Deepgram solves the real-world audio problem and connects with less than 300 milliseconds of latency, making interactions feel like real human talk. What I love most is that Deepgram actually gets how people talk in the real world. The best part of Deepgram is its insane speed, which is the difference between a clunky tool and a natural conversation. The initial setup is generally very straightforward and developer-friendly, especially for their SDK libraries for Node.js, Python, and Go, as well as their documentation and authentication. Review collected by and hosted on G2.com.

TTS language gap, pricing complexity, limited voice styles Review collected by and hosted on G2.com.

I find Deepgram works reliably, and the latency is quite low, which gives the feel of live functionality when transcribing speech. The live transcription feature is really fast, which I find great. For English, Deepgram performs very well and is mostly good for other languages too. Especially for Russian, the quality is superior compared to other tools. I appreciate that Deepgram's cloud is much faster than local alternatives like Whisper, and it's really GDPR compliant, offering EU servers which is a game changer for privacy. The initial setup was actually very easy due to clear documentation and a nice playground to try things before implementation. Review collected by and hosted on G2.com.

I tried using medical transcription, but it only works in English. For my work, it would be better and required to be in German. There's a special model designed specifically for medical language, mainly in English, and I would like to have it in German as well and in other languages also. Review collected by and hosted on G2.com.

I really like the Deepgram Flux model, especially its natural pause detection, which allows my AI agent to transcribe without sending an end event until I'm actually done talking. This feature gives it a more natural conversational ability rather than interrupting me while I'm still talking. I also like that Deepgram is really fast and really cheap. Review collected by and hosted on G2.com.

I mean, I guess it was kinda tricky to do the integration to make it super smooth with my agent, but I got it done, and it works well. Well, I'm using Cartesia for text to speech. And I was hoping to just use Deepgram Text to Speech, but I found that Cartesia has more natural voices. It was really easy except it needed a lot of tinkering to get the word timing working correctly. Review collected by and hosted on G2.com.

I think the SDK and WebSocket API are clean, which made setting up the streaming connection pretty straightforward. Running two separate WebSocket streams for my microphone and system audio worked well, and the connection was stable. The JSON message format also made sense, and the reconnection logic was easy to implement. From a developer experience standpoint, getting the basics up and running felt smooth. Nova three looked really promising with its impressive accuracy benchmarks and good latency numbers. Features like smart formatting and punctuation worked well out of the box. Deepgram has solid technology, and Nova three is a capable model with a good API design. Review collected by and hosted on G2.com.

The first big challenge was actually turn detection. Deepgram fires these utterance end events based on silence and the problem is it fires on every pause, not once per complete thought. So, in a real meeting, when someone is talking and they just pause for a breath or to think for half a second, it results in separate fragments. I spent a lot of time trying to tune utterance and milliseconds. It always felt like I was fighting the system instead of working with it. The second issue was real world accuracy. When I compared what Deepgram transcribed to what Loom captured, the differences were rough. Domain-specific words were getting hallucinated into completely wrong things, like 'contractor role' turning into 'podcast show.' And the key term prompting feature in Nova three, which could have helped, felt static, and I never got it properly integrated during development. The feature could be more accessible or documented better. The third thing was transcript mutability. Deepgram's streaming results are mutable, which makes sense technically, but for a real-time UI, it creates a flickering effect where text keeps changing. This made the experience feel unreliable from the user's perspective. Review collected by and hosted on G2.com.

I find Deepgram's UI to be intuitive, simple, and highly functional, making it easy for users to navigate and complete their tasks. The variety of models like Nova 2, 3, and Whisper allows me to fine-tune my usage based on language needs, which is very helpful for my Oral History Project. The sub-features within the model, such as diarization of speakers, redaction, sentiment analysis, and grammar, make it an excellent tool for working with ASR-related tasks. The fast transcription rates significantly improve time management by transcribing hours of audio in seconds, streamlining my workflow and enabling more interviews. Moreover, Deepgram's API is straightforward to integrate, creating an effortless experience for developing independent tools. The quality of transcriptions is greatly enhanced, and the ability to catalog based on efficiency, success rate, and accuracy is invaluable. Overall, Deepgram is not only reliable and cost-effective but is also a de facto choice for speech-to-text models. It's clearly a 10 for me, and I've already recommended it to colleagues because of the ongoing improvements and planned developments. Review collected by and hosted on G2.com.

The only issue is the inability to rename speakers and the absence of timestamps. I understand JSON files could solve this but it would save a lot of time. It takes me a while to extract all the details like timestamps and speaker changes from a JSON file. Furthermore, processing the word file results in a very large file size. Review collected by and hosted on G2.com.

I found the WebSocket and streaming use to be a lot easier and more consistent with Deepgram, which I also found better for multilingual use. The quality of the model is great, and the streaming functionality is awesome. I appreciated how the API is pretty easy to use, and some of the documentation is helpful. The ease of integration was something I liked, and the $200 free credits gave me a chance to test the quality of the platform, which was cool and provided some return. Review collected by and hosted on G2.com.

I think Deepgram needs to support more languages. It didn't work well with multilingual users speaking multiple languages in the same sentence, which is an issue for my European customers. Also, the real-time transcript doesn't handle voice commands properly, saying 'comma' instead of adding punctuation. It would be great to have low latency like Mac dictation for ease of use. Review collected by and hosted on G2.com.

I love Deepgram for a few reasons. First, their models are phenomenally accurate, which is vital for my extensive speech-to-text applications. I appreciate the flag option they provide to opt out of all data logging, which is super convenient compared to AssemblyAI, where you have to send an email to opt out of model training. I absolutely love the streaming option they have; I get live streaming feedback every second, and that makes it very enjoyable to use. The initial setup was absolutely smooth, and there was virtually no effort involved. I've tried many APIs, and Deepgram's setup was exactly what I expected. Review collected by and hosted on G2.com.

I think one aspect where Deepgram definitely needs to improve is that it heavily penalizes users from opting out of model training program. What they say is that they directly cost you twice as much if you opt out of model training. I think this is slightly unfair and the multiplier should have been less extreme. I think it's fair to cost about 25% to 50% more, but not 100% more. Other than that, I have one feedback for Deepgram. I think it's high time that they release a new model because the landscape is very competitive right now, assembly AI has introduced a newer model and 11 labs has introduced a newer model too. So I hope they introduce a new newer model too because that is how the landscape is evolving. Review collected by and hosted on G2.com.

I use Deepgram for the STT and TTS engine in my Goddo project, an AI buddy for kids, and I really appreciate its excellent latency. The STT transcription is very fast and quickly pushes to the LLM to generate a response, which is crucial for maintaining the kids’ interest. The voices in the TTS are decent and expressive. The $200 credit has been awesome since I haven't spent a single dollar on the Deepgram API so far, allowing me to test it heavily without worrying about the budget. Deepgram is better for my budget compared to other real-time APIs like Cartesia and Rime, which are too expensive. The per-minute cost will be affordable even after the credits are gone. The main things I like about Deepgram are the generous $200 credit and the decent latency, which is fast enough for kids who lack patience. The documentation is very clean and clear, making the setup straightforward. Review collected by and hosted on G2.com.

I think multilingual support is a big problem. The STT does a very good job in transcribing different languages and it's as quick as just English, so the multilingual part is good for STT. However, for TTS, it's a big problem. That is where I end up using Gemini Live Audio because that same voice can do different languages while maintaining the accent and pronunciation. That is definitely something that's missing from Deepgram. Review collected by and hosted on G2.com.