// Media Lab · chapter 06
Some media ships in Revive today: synthetic voices, video replies, retrieved artwork, and AI-generated portraits. The rest is a media pipeline that a sister project tested from start to finish. It is ready to use with the personas.
Already live · on this card
Each persona speaks with its own synthetic voice. Send a voice message, and the mind hears it, finds a grounded answer in its own sources, and replies aloud in character. Sagan and Walter Russell use voice clones, not stock voices. Russell's clone comes from a lecture tape he recorded at Swannanoa in 1953.
Already live · on this card
Gabriella 2.0's "Gabriella Pro" voice was not set once. We calibrated it across several listening sessions until it sounded correct.
Already live · on this card
Gabriella 2.0, Sagan, Decode, and Walter Russell hold live spoken conversations. The channel turns speech into text, writes a grounded answer, and streams the voice back out, at about two seconds of latency. Sagan's channel mixes background music under his answers.
The voice lines come from each mind's own sources. The live bots' synthetic voices read them aloud.
←→ change mind 1–3 pick
Mind 04
Astronomer & science communicator
The candle in the dark
Voice cloneReal-time voice
Corpus · Cosmos + 13 TV episode transcripts
Mind 01
Spiritual teacher & consciousness guide
The reference implementation
Tuned by earReal-time voice/vid replies
Voice · Gabriella Pro · tuned by ear
Mind 07
Critical analyst of the digital attention economy
The largest library
Real-time voiceNot a person
Corpus · 83 courses · 1,030 papers · 815 case studies
The film's portraits
The film's code draws each face with glyphs from that mind's corpus. Point at the portrait to see the words. Each glyph portrait uses about 4,000 characters of that mind's own text, read from its index.
1–8 pick a mind ←→ next · drag or point to wipe
Already live · Voices · video · imagery
Each capability below runs in production, together with the RAG APIs and Discord bots.
/vid repliesLiveGabriella 2.0 answers with video. The system merges a looping clip of her portrait with a new spoken answer. A spoken reply arrives as a short talking clip instead of an audio file. Persona video works in the live system today.
Leonardo has an image-retrieval system. It pulls pieces from his own catalog and pairs them with his replies. When he speaks about anatomy or flight, the applicable sketch comes with the answer.
Some faces on this site are AI-generated portraits. Not all are. A persona's face can also come from the record. Imagery a mind owns (artwork from its corpus, photographs, sketches) can enter the system too, so the mind can answer with its own pictures. The avatars in the strip below this grid are those exact files, live on each page.
The portraits, as shipped
These are the real avatar files served across the site. The partner media pipeline can set these portraits in motion.
This chapter in the film · 0:30 – 0:44
The film introduces the minds on character cards. Carl Sagan's card carries his synthetic voice tag at the lower left. The lines each voice reads come from that mind's own sources.
