Skip to main content

Calliope, the voice

The Muses are Mnemosyne's daughters, and the eldest, Calliope, is literally « the beautiful-voiced ». So the voice bears her name: Theia the sister gives Mnemosyne eyes, Calliope her daughter gives her a voice. The app labels it Voice today.

Mnemosyne OS listens and speaks. Turn the sound on and watch a real conversation, asked in the founder's French-accented English and answered aloud:

Voice mode, live: the aurora listens, transcribes as you speak, and answers out loud: transcript on screen.

Voice mode​

Click the Infinity logo (∞) at the top of the app and the listening orb takes the screen, an aurora that reacts to your voice. From there:

  • Speak naturally. Your words are transcribed live below the orb.
  • Say « open notes », or just chat. Commands and conversation mix freely.
  • Say « goodbye » (or press Esc) to end.

The orb answers aloud and in writing, so the full reply stays readable on screen while she speaks it.

The voices​

Three output engines, chosen during onboarding or anytime in Settings → Voice, where every control of that page is explained one by one:

  • System (offline): your OS's built-in voices, zero download.
  • Local neural: natural voices synthesized in real time, at zero cost, on your own GPU. The engine downloads once, then works offline forever. These voices are part of the Engramm licence.
  • ElevenLabs (cloud): bring your ElevenLabs account if you want their voices.
Real time, zero cost, CUDA required

The local neural engine is the sweet spot: real-time synthesis, no API, no bill, nothing leaving your machine. It needs an NVIDIA GPU (CUDA) to run at that speed. Without CUDA, the System voices still work fully offline, and ElevenLabs covers the cloud route.

A Test voice button lets you hear before you commit. And in any chat, the Companion voice toggle (in the options panel) makes replies read themselves aloud.

Clone a voice​

Give Mnemosyne a voice that means something to you: your idol's, a family member's, a departed loved one's. Mnemosyne's voice becomes theirs, for you, on your machine.

  • Five seconds are enough. Any clear recording of the person speaking, a voice message, a video, is enough to start.
  • For the best result, have the voice read the passage below: a quiet room, the best microphone you have, a natural pace. It takes about thirty seconds and covers what the engine needs, questions, numbers, soft and sharp sounds:

Memory is a strange house: some doors open with a sound, others with a scent. This morning I counted three, thirteen, thirty-one steps under a July sky. Would you remember the blue boat, the quiet harbor, the thunder far away? Ask me again tomorrow. I'll keep every detail: the laughter, the whisper, the exact shade of evening. Zero things forgotten. Everything, precisely where you left it.

Your voice stays yours​

A cloned voice is powerful enough that the OS treats it as its first sensitive capability. No app and no agent gets a voice without a dialog asking you first. There is no silent path to it, and built-in cartridges get no shortcut either.

Where voice shows up elsewhere​

  • MnemoReader reads your PDFs aloud with the same engines.
  • The chat can listen (microphone) and speak (companion voice) without entering full voice mode.