Vibe Coder - Talk with AI to build products—in VS Code, Cursor, Windsurf

Karpathy coined the term "vibe coding" to describe creating without going deep into code by just talking to your computer, describing what to build, debugging as you go, and talking it out. Vibecoder let's you do this with a VScode/Cursor/Windsurf extension.

Sharon Yeh

6mo ago

Shortcut - Your AI partner that works at the speed of voice

Transform the way you work with Shortcut. No more typing, just natural conversation. Get instant answers, turn your thoughts into solutions, and draft messages, emails, and docs in seconds —all while staying in your flow.

Deepgram just released Nova-3 (real-time multilingual speech-to-text) - beta access?

Just received an email about Nova-3. Looks really interesting. We have been playing around with real-time language switching on our phone calls. Looks like Nova-3 would support way more languages beyond just English and Spanish. Could be a game changer. Hoping to get beta access to the API soon.

Kat Manalac

5yr ago

Deepgram MissionControl - Train and deploy speech AI models for free

Deepgram MissionControl is the first and only platform for training end-to-end deep learning speech recognition. Train a speech model to understand your accent, product names, and more within a few clicks or API calls.

Jared Friedman

7yr ago

Deepgram Brain - Drag and drop speech transcript editor that learns from you

Deepgram Brain is an AI transcript editor that makes it easy to drag and drop recorded files to edit. Transcription happens automatically and access to the editor is totally free. Use it to transcribe meetings, lectures, podcasts, do closed captions or just get free Speech-To-Text. API and Python SDK available for developers.

Jason D. Rowley

2yr ago

Speech-to-Text API by Deepgram Nova - Next-Gen Speech-to-Text with Unmatched Performance

Nova is the world's deepest-trained ASR model to date, achieving unrivaled performance across diverse automatic speech recognition tasks. Nova delivers a 22% reduction in WER, 23-78x faster inference, and 3-7x lower cost than its closest competitor.