Deepgram Reviews

1. suz11

   about 3 years ago
   Fast

   It's fast - but for an API, not the fastest speech-to-text. For a long while I hadn't done research and trusted them. Then tried Whisper and Picovoice. On-device latency is nothing comparable with cloud APIs. If latency is important go with Whisper or Picovoice. If customization is also important go with Picovoice.

   don't get me wrong it's still faster than amazon, Microsoft or Assemblyai

   Competitors: Picovoice.ai, Google Cloud Speech API, AssemblyAI, Speechmatics, Microsoft Azure, Amazon

   Pros:    Fast|Fast sales|A free demo|Supports multiple languages

   Cons:    Slow support for free customers|Limited free version

FastAPI Reviews

1. Kurslog team

   · Working at Kurslog · 5 months ago

   When our backend team needs to build services for data parsing, aggregators, or high-load APIs, FastAPI is our absolute go-to choice. It completely lives up to its name-development speed is outstanding.

   The combination of Pydantic for data validation and built-in async support keeps our shared codebase clean, strictly typed, and reliable. But the biggest highlight for our cross-functional team is the automatic generation of interactive OpenAPI (Swagger) documentation. Our frontend and mobile developers no longer have to wait for backend engineers to manually update API docs; everything stays perfectly in sync automatically. It has drastically improved our team's communication and delivery speed.

   Competitors: Django, Flask, ExpressJS, Nest.js, Spring Boot

   Pros:    Blazing fast performance (on par with nodejs and go)|Native asynchronous support out of the box|Automatic, interactive documentation generation (swagger/redoc)|Strict typing and data validation with pydantic

   Cons:    Smaller plug-and-play ecosystem compared to older frameworks like django|Requires our architects to design the project structure and directory layout from scratch

Deepgram mentions (34)

• Deepgram: $200 Free STT That Makes Voice Coding Actually Work

  Deepgram changed the maths. Their Nova-3 model does real-time streaming transcription fast enough that the text appears as you speak, not after. And the free tier gives you $200 in credit, which is roughly 12,000 minutes of transcription. That's a lot of talking before you pay a penny. - Source: dev.to / 4 months ago

• The 8 Best Platforms To Build Voice AI Agents

  Deepgram is a voice AI application creation platform. Developers can use its API to build audio apps with text-to-speech, speech-to-speech, and speech-to-text models. To experience and see how Deepgram works, visit the URL above and try the interactive, real-time voice demo on the home page. - Source: dev.to / 6 months ago

• From Cameras to Action: Real‑World Applications of Vision and Speech AI

  Modern ASR systems (such as Whisper, Deepgram, or custom domain-tuned models) are now robust enough to operate in factories, warehouses, and construction sites where noise floors routinely exceed safe listening levels. - Source: dev.to / 8 months ago

• The ultimate open source stack for building AI agents

  Start by hooking up speech-to-text (STT) using something like OpenAI’s Whisper if you’re going open source, or Deepgram if you want a super-accurate plug-and-play API. - Source: dev.to / over 1 year ago

• 10 Ways AI Can Speed Up your Mobile App Development

  Deepgram specializes in real-time transcription optimized for specific industries and use cases. - Source: dev.to / over 1 year ago

FastAPI mentions (312)

• I Built My First Machine Learning API — Here's Everything I Learned

  I used FastAPI, a Python framework built specifically for creating APIs quickly, with automatic validation and interactive documentation baked in. - Source: dev.to / 20 days ago

• Shipping Sovereign SDK: Cryptographic Forensic Receipts and the End of the AI "Prose Tax"

  The Sovereign SDK is a Python-native framework designed to minimize prose overhead while generating ironclad, cryptographic execution receipts for AI agents, complete with drop-in FastAPI/Starlette ASGI middleware. - Source: dev.to / 3 months ago

• 5-Minute AI Jobs and Closed Tabs — Why We Built Replay-Then-Tail SSE

  We had a feature in production where a single user request could run for five-plus minutes — fetch documents, chunk them, hit an LLM per chunk, synthesize a final answer. We did the obvious thing first: a FastAPI handler that ran the pipeline and streamed progress back to the browser over Server-Sent Events. - Source: dev.to / 4 months ago

• FastAPI With LangChain and MongoDB

  FastAPI is a Python framework for building APIs quickly, efficiently, and with very little code. - Source: dev.to / 5 months ago

• I Built A " CrowdSense AI " : A Scalable, Context-Aware Platform for Smart Stadiums

  Backend: Python-based FastAPI for its asynchronous I/O capabilities and rapid JSON serialization. - Source: dev.to / 5 months ago