Navigate

Quick find

Navigate NeuroForge

Esc

Start typing to search public pages and evidence.

    Four pairs · about five minutes

    Can you hear a meaningful difference?

    Compare the qualified LuxTTS control and ERAIS K7 speech route with their roles hidden. Rate both clips, choose A, B, or a tie, then send one response.

    Qualified audioRoles concealedProduct feedback · not MOS

    Why this set is open

    Machine-screened, then heard by a human.

    All eight clips passed the retained waveform and intelligibility gates. Both routes transcribed with zero word errors on these four prompts. The first complete operator review called the result good overall, with slight electronic distortion still worth measuring.

    K7 sparsifies two learned projections in one vocoder block. It does not represent 87.5% of LuxTTS or prove whole-model efficiency.

    Prompts
    4
    Required decisions
    8 ratings + 4 preferences
    Speech recognition
    0% WER · both routes
    Mean pace
    177.4 words/min
    ERAIS K7 STOI
    0.9966
    Collection limit
    500 complete responses

    Before you begin

    A small product-feedback task.

    Taking part is voluntary, unpaid, and for adults 18 or older. Your choices help prioritise speech-quality work. This convenience sample is not a formal research study and cannot establish population preference, scientific MOS, model superiority, or production readiness.

    Nothing is sent until you press Submit. You can stop by closing the page beforehand. Once submitted, the pseudonymous response cannot be linked back to you, so individual withdrawal is not possible.

    What is—and is not—kept

    One accepted record contains four A/B/tie choices, eight 1–5 ratings, the exact study identity, a random HMAC-protected pseudonym, and acceptance/expiry times. It is deleted after 30 days.

    NeuroForge does not ask for or retain your name, email, account, demographics, free text, IP address, playback history, listening time, or per-clip interaction telemetry with the response. Cloudflare still processes ordinary request and anti-abuse signals to deliver and protect the page.

    Collection closes automatically at 500 complete responses. Incomplete browser choices are never collected.

    Questions: privacy@neuroforge.io · Privacy notice

    Concealed comparison

    Listen to A and B, then decide.

    Each clip must finish before its rating unlocks. There is no assumed midpoint.

    Checking collection
    0 of 8 clips heard0 of 12 decisions madeNothing sent yet
    Pair 1 of 4: Lantern

    Pair 1 of 4

    Lantern

    Speech · roles hidden

    A quiet lantern glowed beside the window while rain softened the empty street.

    Sample A48 kHz · mono
    Sample B48 kHz · mono
    Which version do you prefer overall?
    Pair 2 of 4: Folder

    Pair 2 of 4

    Folder

    Speech · roles hidden

    Please carry the blue folder upstairs and place it beside the wooden clock.

    Sample A48 kHz · mono
    Sample B48 kHz · mono
    Which version do you prefer overall?
    Pair 3 of 4: Question

    Pair 3 of 4

    Question

    Speech · roles hidden

    Can a careful machine explain its choices clearly when the answer is uncertain?

    Sample A48 kHz · mono
    Sample B48 kHz · mono
    Which version do you prefer overall?
    Pair 4 of 4: Table

    Pair 4 of 4

    Table

    Speech · roles hidden

    Fresh oranges, warm bread, and silver spoons were arranged across the table.

    Sample A48 kHz · mono
    Sample B48 kHz · mono
    Which version do you prefer overall?

    One atomic response

    Review and send

    Checking the protected collection route. Your choices remain only in this tab unless the complete response is accepted.

    Finish all eight clips and twelve decisions.

    Exact release identity

    The audio and collection contract are hash-bound.

    Every WAV filename is its SHA-256 identity. The release also binds the machine qualification, operator review, source/data rights, and bounded collection authority.

    Study SHA-256
    bc0841031cecc1abbecdb5a0b0b9f49a5e6c9647df7c32e072f3a024c4dcdd27
    Qualification
    d4e018132b5b86fac5f7a3f75a05e3bcf76e9b87e8a39bf4dc519389e6733686
    Operator review
    f68f9142e5535d6656e57358fad960ffd754daff4b6beacacbc4be0574c3ba23
    Rights receipt
    428e7016d8eba3b9a918b3a7f40c460dde2159aa56f30c8c90139d73fa7a5b21
    Collection authority
    5eb294255b4cb3dca03c1eb119cef20878f113a264ad8d09deea599c7342baaa
    Published audio
    8 WAVs · 5.0 MB

    Sources and rights

    A bounded, attributed release.

    The reference voice comes from LibriSpeech (OpenSLR SLR12), prepared by Vassil Panayotov with assistance from Daniel Povey and licensed under CC BY 4.0. No endorsement is implied.

    LuxTTS and upstream ZipVoice are identified as Apache-2.0 projects in the retained rights receipt. The generated clips are published only for this bounded feedback task.

    The A/B roles stay concealed while collection is open. Model weights, private traces, checkpoints, and training material are not distributed by this page.