Existing Neural Doom visual master with its own audio; the four live players are separate.
Open the related pageERAIS / V6 film room
The V6 film room.
Approved voice. Open evidence.
The approved 185.11-second founder-voice anchor is published with its measured captions and transcript. The five V6 demonstration narration clips are candidates pending founder approval, so their audio is withheld; their scripts and event provenance stay visible in the arena.
Film identity
| Approved master | 185.11 s · 24 kHz · founder-voice anchor |
|---|---|
| Web encode | 185.108 s · AAC · 2139 KiB |
| Captions | 38 cues · VTT/SRT pinned |
| V6 candidate clips | 5 · audio withheld |
| Visual masters | 3 separate masters |
| Evidence | V6 discovery arena |
Only the approved V5 voice anchor is published as audio. The V6 clips await founder approval.
Approved narration / captions / transcript
Listen to the approved anchor.
This is the approved V5 founder-voice master, 185.11 seconds, with its measured captions. The player carries the approved audio only; the visual masters below are separate artifacts, not a synchronized render.
Transcript — 11 segments
- Field note, twenty-second of November, twenty twenty-six. This is a long-form test of the ERAIS native presentation voice: one founder capsule, one continuous session, no donor runtime in the inference path.
- The pipeline has four visible stages. Text is normalised, phonemised and mapped to a fixed token table. A four-layer Zipformer text encoder turns those tokens into a conditioned sequence.
- A five-stack acoustic velocity network integrates four anchor-flow steps, each step predicting a clean mel trajectory from the current state, the text condition and a six-second speech reference.
- The final mel is decoded by a native forty-eight kilohertz Vocos graph: eight ConvNeXt blocks, two upsampling stages, two ISTFT heads, a sinc resampler and a Linkwitz crossover.
- The voice itself is a reference-free capsule: the conditioning tensors learned from the approved take, stored as ordinary float weights. Inference does not need the source recording.
- For the first time, the same acoustic and vocoder parameters execute through ERAIS-owned graph code. The imported weights remain explicitly attributed.
- The important engineering question is no longer whether the voice can run without the donor. It is which operations deserve native weight-space programs, which should remain deterministic DSP, and where the current fracture boundaries waste time or constrain expression.
- The measurements in this run separate tokenisation, text encoding, four velocity calls, and vocoder decode. They also count attention score maps, feed-forward projections, convolution branches and memory high-water marks.
- That matters because a two-minute waveform is not one model call. The qualified context is roughly forty-two seconds including the reference, and full attention grows quadratically. Long-form narration therefore uses the largest context-safe segments and one continuous voice state, not a single impossible forward pass.
- The next upgrades are targeted. Replace repeated dense projections with composable weight-space banks. Make attention, feed-forward and convolution schedules parametric and measurable. Cache immutable conditioning and reference structure. Increase segment size where the context allows.
- Then compare every change against this same founder voice on naturalness, cadence, pronunciation and long-form consistency.
Existing visual masters / separate audio
What the film can show.
These are the existing visual masters, reused unchanged. Each has its own audio and page; none is presented as a synchronized 185-second render of the approved narration.
Existing founder-story visual master; its narration is separate from the approved V5 anchor.
Open the related pageExisting practical-AI visual master; it is not a synchronized 185 s render.
Open the related pageV6 candidate narration / approval boundary
The V6 clips are not published yet.
The five V6 demonstration clips are candidates pending founder approval. Only their metadata, caption counts and hashes are listed; no candidate voice audio is present on this page or in the public media directory.
| Clip | Duration | Caption cues | Status |
|---|---|---|---|
V6 master (candidate)00_master | 260.8 s | 52 | audio withheld |
Autonomous discovery01_discovery | 54.5 s | 11 | audio withheld |
Generalization and consolidation02_generalization | 45.1 s | 9 | audio withheld |
Neural Doom Cyborg03_cyborg | 46.7 s | 9 | audio withheld |
Native voice04_voice | 33.7 s | 8 | audio withheld |
The five v6 narration clips are candidates pending founder approval. No candidate audio is published; only metadata, captions hashes and scripts are listed.
Evidence / links
Follow the claims.
The film points to the source-pinned evidence rather than replacing it. The approved anchor, the V6 discovery arena, the live players and the execution observatory remain separately inspectable.
Release receipt: reports/agi_flagship_v6/agent_b_public_release.json
Claim boundary
- The approved V5 master is the founder-voice anchor; it is not a V6 demonstration-script film.
- The v6 demonstration narration is pending founder approval and is withheld.
- The visual masters are separate audio/video artifacts, not a synchronized render.
- Model-based voice metrics are proxies, not a blinded human MOS study.
- Donor-origin acoustic/vocoder weights remain; WSP coverage is partial.