It’s about value—saving time, money, and effort. Traditional transcription services charged $1-2 per audio minute. Imagine needing 10 hours transcribed—that’s $600 to $1,200, just to get your words on paper. With tools like Assembly AI charging $0.015 per minute (that’s $0.90 for an hour), the cost drops dramatically. For companies dealing with large volumes of audio, this is a game changer. - Source: dev.to / over 1 year ago

The auto caption is from assemblyai.com, they do a pretty good job. As for manual, you can do `Add Layer` > `Text` from the short-form editor then trim each text layer. Its slow going though. Ideally we will figure out a better interface and build it. For now I recommend using the auto caption, then modifying it to your liking, if there is more than a few words it will probably be faster. Thanks for the kind words! Source: about 3 years ago

Assemblyai is a great tool for extracting transcripts from videos, I have used it for investor presentations from other sources. - Source: dev.to / almost 4 years ago

AssemblyAI is pioneering accurate and accessible speech recognition powered by cutting edge Deep Learning, Machine Learning, and AI research. Its Speech-to-Text API transcribes audio and video files and live audio streams with industry-best accuracy. In addition, the company offers Audio Intelligence APIs that secure higher ROI for users, including Sentiment Analysis, Topic Detection, Content Moderation, Auto... - Source: dev.to / over 4 years ago

Check out http://assemblyai.com/ - the API has pretty good Diarization results and is free for small volumes of data. Source: over 4 years ago

Memory. I use Supermemory for this. Before, Pipa loaded context files and knew to update them. A memory tool adds teammate-like recall: goals, preferences, latest business state, and small details that should carry across runs. Good memory tools also know how to supersede and delete memories, which matters once the agent has more autonomy. - Source: dev.to / about 2 months ago

We wire everything up with Vision Agents as the voice agent framework, Stream for WebRTC audio and video, OpenAI Realtime for speech in and speech out, Anam so the agent shows up as a face on the video, and Supermemory so answers come from search over your uploaded documents instead of guesswork. The code stays small and most of the behavior lives in one registered function that asks the memory store for relevant... - Source: dev.to / 3 months ago

My friends and I are working on https://supermemory.ai, an AI second brain to help you remember content from saved webpages and notes. - Source: Hacker News / almost 2 years ago