Tellie Prompter 1.5
The teleprompter that knows what you haven't said
What it does
Most teleprompters make you follow them. Tellie follows you. It listens to the words you actually say, so you can pause, skip, improvise, or go off script without losing your place. Now Tellie 1.5 knows what you haven’t said yet, too. It tracks your important points, warns when you’re running long, and debriefs your take. All in a 3 MB Mac app that runs locally, with no account and no telemetry. Free for 10 days and $10 off for ProductHunt with code PRODHUNT10
Tellie Prompter is the Mac teleprompter that understands. It knows what you
Tellie knows what you’re saying, keeps your place, and remembers what you’ve covered . Voice Follow: Tellie follows your voice, word for word. So you can pause, skip, ad-lib and Tellie waits for you. Privately, on-device. Talk too fast and you leave the script behind. Pause and it keeps marching. Go off-script and you hunt for your place. Speak like a person. Tellie tracks the words you actually say, credits a point when you make it in your own words, and keeps your place even when your delivery isn't perfect. Every prompter scrolls. Only Tellie listens, keeps score, and disappears. Watch: Pause. Skip. Ad-lib. Tellie follows the words you actually say, even when they’re…from tellieapp.com
Pricing, as stated on its site
Free tier, paid plans from $29/mo — Free for 10 days with full features, then $29 one-time payment for Tellie Pro. No subscription required.
checked September 2026 · prices change
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com