Local-first meeting and interview recorder that transcribes, labels speakers and writes up your notes entirely on your own computer, for a one-time price.
Summary
Voice-first personal AI agents with continuous memory across voice and text — four distinct personalities, ultra-low latency, free on iOS.
Screenshots
Description
Sesame builds conversational agents that are designed to be talked with rather than typed at. The company became known for the unnervingly natural speech of its Maya and Miles voice demos; the iOS app is that research turned into a product you can keep in your pocket.
The core claim is conversational timing. Sesame agents run at low enough latency to hold a real back-and-forth, and — more unusually — they are built to judge when to answer, when to keep listening, and when to stay out of the way. That last behaviour is what separates a conversation partner from a voice interface that talks over you. When a thread goes somewhere useful, the agent acts on it: searching the web, writing notes, setting reminders, and summarising what you worked out.
You pick one of four agents — Maya, Miles, Simone or Charlie — each with its own personality and point of view, and each carrying memory that accumulates through use. Memory is continuous across voice and text, so a thought you spoke this morning is still there when you type this evening.
On privacy, Sesame states that conversations are private, that data can be deleted at any time, and that Incognito mode saves nothing to memory or to Sesame's servers, with no advertising and no data sale. Typical uses the company describes are curious exploration, brainstorming out loud, and rehearsing a difficult conversation with something that has no stake in the outcome.
The app is free and iOS-only, currently labelled a preview; Sesame has said it is heading for intelligent eyewear in 2027. The catalogue's existing voice entries — ElevenLabs, Cartesia, Hume — are developer platforms; Sesame is the consumer end of the same technology.
Reviews
Similar App Suggestions
Local-first Mac dictation that types into any app, plus file and link transcription across 110 spoken languages on Apple Silicon.
Voice dictation that works in every app and cleans up as you speak — no filler words, correct formatting, right tone.
Privacy-first voice to text for macOS, Windows, and iOS — runs offline on-device with customisable AI modes.
High-quality stem separation — split any track into vocals, drums, bass, and instruments with minimal artefacts.