
Mem
Notion
Obsidian.md
Tana
Logseq
Reflect
Supermemory
Evernote
Deepgram
Eleven Labs
Vapi
Speechmatics
AssemblyAI
Cartesia Sonic
Otter.ai
Fraim
Mem
DeepgramIt'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
Based on our record, Deepgram should be more popular than Mem. It has been mentiond 34 times since March 2021. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
Eg https://get.mem.ai/ approach or https://beta.omnilabs.ai/ But then tailored to Obsidian. Source: over 3 years ago
I use Notion but I have heard that the andriod experience is not the best. You may want to try Coda, Obsidian, Mem or Anytype. I know of a few others but I think for the purpose of a second brain these can do the trick itโs just about preference and which experience you like the most. Source: about 4 years ago
Https://get.mem.ai right now it isa web app they have an iOS app in beta. Source: about 4 years ago
For supervising the trauma team I've also been playing with "Mem". https://get.mem.ai/. Source: over 4 years ago
I really love obsidian. Sure I t has a couple of wrinkles, the mobile app is new still and has a couple more wrinkles, but it scratches so many itches I have around note taking. Currently using it alongside https://get.mem.ai/ and love the pairing for knowledge base and real time notes. Iโm working from n combining the two to come up with my ideal set up. - Source: Hacker News / almost 5 years ago
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 / 3 months ago
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 / 5 months ago
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 / 7 months ago
Start by hooking up speech-to-text (STT) using something like OpenAIโs Whisper if youโre going open source, or Deepgram if you want a super-accurate plug-and-play API. - Source: dev.to / over 1 year ago
Deepgram specializes in real-time transcription optimized for specific industries and use cases. - Source: dev.to / over 1 year ago
Notion - All-in-one workspace. One tool for your whole team. Write, plan, and get organized.
Eleven Labs - The most realistic and versatile AI speech software, ever. Eleven brings the most compelling, rich and lifelike voices to creators and publishers seeking the ultimate tools for storytelling.
Obsidian.md - A second brain, for you, forever. Obsidian is a powerful knowledge base that works on top of a local folder of plain text Markdown files.
Vapi - Voice AI Infrastructure for the Internet
Tana - Welcome to the future of work. Build anything. Use it for everything. Kill your SaaS subscriptions.
Speechmatics - The most accurate and inclusive speech-to-text API ever released.