Music and sound design

Music generation, scoring, Foley, ambience, stems and mixing

• articleDo Wwise's music transition rules treat a segment's Exit Cue as a legal 'Next Grid' exit point, per any retrievable source?
  The only retrievable source is a user feature request (Wwise 2021.1.6), not documentation. It reports that 'Exit source at Next Grid' does not treat a segment's Exit Cue as an exit point even when the cue falls on a grid line, so transitions can be delayed to the next grid point; users work around it with custom cues on the grid and Next Cue exits. The vendor reply only thanks the poster, so the behaviour is neither confirmed nor denied, and later versions are unknown.
• articleWhat is a pansori performance made of (who performs, which channels alternate, what the drum cycles are for), as a first orientation before borrowing anything for screen or audio narration?
  Partially verified: the curator re-read none of the cited sources; S4, S1, S2, S3 rest on the producer's pinned reading. Pansori is a solo narrator-singer (sorikkun, also called gwangdae in older usage) telling one long story with a drummer (gosu): the singer alternates sung passages (sori/chang) and spoken passages (aniri) and adds mimetic gesture (ballim), while the drummer supplies rhythmic cycles (jangdan) and shouts of encouragement (chuimsae). One programme page states that the poetic aspect is amplified to signal the shift from spoken to sung passages, and that jangdan are chosen to respond to changing mood or context. Five stories are canonical and each full telling takes hours. The sources read do not spell out that one voice plays every character; they say the singer 'plays the central role' through song, speech and gesture.
• articleWhat exactly did the auditory Kuleshov experiment (Baranowski & Hecht) do and find about music and judged emotion of a face, what are its limits, and what do its stimuli rights look like?
  Read from the author's dissertation (Chapter 7, the 'in press' version; the journal body is paywalled and was not read, though the journal abstract matches). Thirty psychology students (21 female, 9 male, 20-31 y) watched 27 clips (3 per cell of a 3x3: music happy/sad/none x final-face expression neutral/happy/sad). Each 21 s clip: actor looking at a screen for 3 s, a 15 s muted neutral YouTube scene, 3 s final reaction. Music was unknown, instrumental, composer-categorised film music from online databases. Ratings: six basic emotions 0-5, with happiness and sadness analysed. Music affected happiness (F(2,58)=9.52, p<.001, partial eta squared .25) and sadness (F(2,58)=3.29, p=.044, .10) ratings; sad music lowered happiness ratings; happy music lowered sadness ratings versus sad music; sad music did not raise sadness significantly above no music; ratings had a floor effect. Stimuli rights (music databases, YouTube scenes) are not stated.
• articleWhat does the AAF Edit Protocol document for audio interchange (gain, pan, fades, sample rates), what must an importer do with unsupported effects, and what do converters state they do not carry?
  The AAF Edit Protocol carries audio gain (Mono Audio Gain, clip and track), pan (Mono Audio Pan on mono essence only), fades and crossfades and MIDI, requires one edit rate and sample rate for all audio tracks in a file, and lets importers ignore unsupported effects provided they log it; it has no plug-in concept, so plug-in processing does not travel in an Edit Protocol AAF.
• articleHow does spatial audio for XR/immersive delivery (ASAF/APAC, IAMF, MPEG-H, OpenXR) differ in role and scope from the cinema/broadcast Audio Definition Model (ITU-R BS.2076-3)?
  Partially verified: the curator re-read S14, S18, S2; S13, S15 were not re-read by the curator and rest on the producer's pinned reading. ADM (ITU-R BS.2076-3, 2025) describes audio rather than carrying it: channels are typed DirectSpeakers, Matrix, Objects, HOA or Binaural, with head-locked and headphone-virtualise parameters, and the audio travels in BW64 with rendering left to a separate renderer. Apple's ASAF, by contrast, packages metadata with linear PCM in Broadcast Wave and depends on Apple's built-in renderer, which adapts to object and listener position and orientation; it is streamed as APAC. The Apple talk does not mention ADM, and no inspected source documents converting an ADM master to ASAF. IAMF combines audio elements and mix presentations for device-specific rendering.
• articleWhich spatial-audio formats and APIs do public XR and immersive-delivery documents actually define (Apple ASAF/APAC, IAMF, MPEG-H, glTF MPEG_audio_spatial, OpenXR, WebXR, Web Audio), and where is there nothing to read?
  Partially verified: the curator re-read S2; S11, S13, S14, S15, S16, S17 were not re-read by the curator and rest on the producer's pinned reading. Spatial audio is defined at different layers: Apple uses ASAF for production and the APAC codec for delivery (APAC required for Apple Immersive Video); AOMedia's IAMF is an open model and container for channel, ambisonic and object audio with binaural rendering signals; WebXR defines no audio of its own (web apps rely on Web Audio). No single open format spans production, delivery and XR playback in the documents read.
• articleBefore I put AI-generated Foley into a delivery, what per-component rights and provenance checks do the sources imply an audio post agent must make?
  A synthesis from the pinned licences and cards: (1) record model, checkpoint and revision; (2) read the weights licence (CC BY-NC, Tencent community licence with Territory limits, or conflicting statements) against the delivery's commercial status; (3) check output clauses (Tencent: no ownership claim but no use to improve other AI models and no use outside the Territory); (4) check each auxiliary component (VAE, Synchformer, vocoder, CLIP) for its own licence; (5) note training-data statements the card disclaims (MMAudio) or omits (HunyuanVideo-Foley paper); (6) log provenance marks (Google V2A research applies SynthID; Veo 3 card cites SynthID) and any required notices; (7) escalate conflicts to a human rights owner. This is a checklist proposal, not legal advice.
• articleWhat do the authors of video-to-audio models say the models get wrong, so I know what not to ask of them?
  Documented failure modes cluster: speech and lip sync (MMAudio 'unintelligible mumbles'; Google V2A 'uncanny lip-syncing'; Movie Gen does not support voice), dense, small or occluded motion (Movie Gen: tap dance, footsteps), unfamiliar sound concepts (MMAudio: 'RPG firing'), unrequested music (MMAudio), dependence on clean input video (Google V2A), and long-form or precise-timestamp reasoning (ThinkSound's MLLM). These come from the model authors' own statements; none was reproduced.
• articleI have a silent or AI-generated video clip and want a sound track: what kinds of video-to-audio systems exist, what do they take in and put out, and which of them can I actually run?
  Primary sources split into measured open systems (MMAudio, HunyuanVideo-Foley, ThinkSound: video plus optional text in, audio out, weights on Hugging Face), a measured closed system (Meta Movie Gen Audio, 13B, 48 kHz, up to 30 s per pass plus extension, described as research-only), and vendor showcases (Google V2A blog, Veo 3 joint audio) that give no sample rate, duration or sync metric. Sample rate and clip length differ by system; only the open ones can be inspected or run, and their licences differ (see G033 candidates).
• articleConverting a BWF/BW64 master to FLAC and then Ogg Opus: which metadata and channel information does each format's standard give a place for, and which has none?
  Partially verified: the curator re-read none of the cited sources; S10, S7, S8, S9 rest on the producer's pinned reading. BW64 carries bext and ADM (chna links tracks to ADM IDs), FLAC can carry Vorbis comments and foreign RIFF/W64/AIFF chunks in application blocks, and Ogg Opus carries Vorbis-style comments with R128 gains and a different channel order; no standard read defines a mapping of bext TimeReference or ADM chna into FLAC or Opus, so preservation of that metadata is tool-specific (producer synthesis, not executed).
• articleAI music video pipeline (Suno + Seedance audio-sync): feed vocal-only stems or the model lip-syncs the instruments; fix drift with a dedicated lip-sync pass and edit to the track
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. R2 (Apr 2026): lyrics drafted with an LLM, song made in Suno v5.5 with a structured prompt (concept, voices, chorus/outro, BPM, language) and "exclude styles" used as a negative prompt. Characters: character sheets, then many photos per character (33, 41 and 57) to train a custom character model on the host platform. Lip-sync shots framed as close wide-angle (8 mm-style) singing-to-camera. Key failure: when the full mix is uploaded, Seedance lip-syncs instruments too, and it can alter or invent lyrics in the audio track; fix by exporting Suno stems (Pro tier) and uploading the vocal stem only, then running a separate lip-sync pass with the same vocal stem. Dance shots c...
• articleCreator licensing claims vs provider terms: a Mureka tutorial promises "100% royalty-free... commercial license... no copyright strikes" while Mureka's terms are narrower
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mikkel Lassalle's Mureka video (2026-03-03, R8) tells viewers that all generated tracks are "100% royalty-free and come with a commercial license" and that "you don't have to worry about any copyright strikes". Mureka's own terms as fetched (C3-B413-01, R13) say: paid-tier users own Output; FREE-tier Output is owned by Mureka; the general service licence is for personal, non-commercial use; Mureka does not guarantee copyright registrability and the user bears legal risk; using Mureka's distribution service grants Mureka an exclusive licence. No term read guarantees freedom from copyright claims (Content ID or otherwise). Lesson for curation and creators: a sponsored tut...
• articleWhat does MusicXML 4.0 define for notated versus sounding (MIDI-compatible) data, and what do its own version notes say changed for MIDI tooling and file structure?
  Partially verified: the curator re-read S2, S5; S1, S3, S4, S6 were not re-read by the curator and rest on the producer's pinned reading. MusicXML's own tutorial splits the format into notation (display/print) elements and sounding elements that support MIDI playback, of which only the sounding elements are required; durations follow MIDI as divisions per quarter note; version 4.0 removed the midixml DTD/XSL without XSD replacements. No MusicXML text read enumerates conversion losses.
• articleHow is an all-night Javanese wayang kulit purwa performance divided (the three pathet) and what scene types are described in each part?
  Sources agree that an all-night Surakarta-style performance is divided into three pathet (nem, sanga, manyura) played in that order, each built from a palace court scene (jejer), further scenes (adegan) and typically a battle (perang), and that the dalang (puppeteer-narrator-singer) controls the sequence with sung suluk, narration and music cues. Times differ: one article gives 9 pm-12, 12-3, 3-5; an outreach handout gives 9 pm to about 6 am. A common outline: pathet nem sets up characters and the problem, pathet sanga holds the hero's withdrawal and, optionally, clown scenes, pathet manyura brings battles and resolution. Scene-level sequences in published lists differ by source and style.
• articleHow do public specs label music and effects stems, and what rights information accompanies stems versus cue sheets?
  Delivery specifications label stems by what they contain, not by who owns them: AS-11 X9 uses MCA tags such as Music and Effects (ggME) and Audio Description (ggAD), EBU R 123 calls the M&E bed International Sound, and Paramount requires Atmos beds and objects separated at least into dialogue, narration, music and effects. None of the stem rules read carries rights metadata; identifiers and ownership (ISRC, ISWC, society, owner and shares) live in music cue-sheet formats such as CISAC AVR+.
• articleWhat do practitioner accounts say about Wwise interactive-music transitions, state-driven switching, layering and their failure cases when official Wwise docs are unreachable?
  A 2018 practitioner tutorial on Wwise state-driven music describes transitions that wait for a sync point (such as the next bar to the destination's entry cue) and says a second state change before that point reverts the pending transition if the destination segment has not started; segments added to one state need their own transition rules, so design complexity grows quickly and designs should stay simple; an intensity parameter can drive states through an RTPC curve. A library composer adds that horizontal (re-sequencing) music is tricky because pieces must cut together. These describe practice, not the vendor's specification, for an unstated Wwise version.
• articleWhich cues tell a listener how far away a voice is (level, direct-to-reverberant ratio, high-frequency loss, vocal effort), and with what numbers?
  Problem: a clean generated voice sounds 'in the listener's ear' regardless of shot scale; placing it at distance needs the right cues together. Conditions: dialogue or narration to sit at a stated distance in a scene. Method (review of the psychoacoustic literature): (1) Level: in an anechoic field level falls about 6 dB per doubling of distance, less in reverberant rooms (about 4 dB per doubling in one auditorium); level is a relative cue, confounded by source level and directivity. (2) Direct-to-reverberant energy ratio (DRR): direct sound falls 6 dB per doubling while reverberant energy changes only about 1 dB per doubling, so DRR falls with distance and listeners hear that as farther; perception is most accurate when level and DRR are both present. (3) Spectrum: air absorption removes high frequencies, and sounds with less high-frequency content relative to low are judged farther. (4) Speech-specific: vocal effort changes the spectrum (shouted speech has more high-frequency ener...
• articleWhat does Fréchet Audio Distance measure, how is it computed, and what did its original paper show about correlation with human judgments?
  Problem: judge a set of generated or enhanced audio clips without a clean reference per clip. Conditions: a reference set of good audio and an evaluation set (the sample-size findings below show N matters). Method (Kilgour et al., 2019): extract embeddings with a pretrained audio classifier (VGGish) from both sets, fit a multivariate Gaussian to each, and compute the Fréchet distance between them; lower is better. The paper proposed FAD as a reference-free metric for music enhancement and validated it against artificial distortions; it reports a correlation of 0.52 with human perception ratings versus 0.39 for signal-to-distortion ratio, -0.15 for cosine distance and -0.01 for magnitude L2 distance. The authors note VGGish ignores phase and uses mel-scaled bins, so some distortions could go undetected. Failure modes: it compares distributions, so it cannot judge a single clip; it depends on the embedding and reference set; 0.52 is a moderate correlation. Limitations: designed for en...
• articleDoes KAD fix FAD's Gaussian and sample-size problems, and how large must N be?
  Problem: choose a distribution-distance metric for small evaluation sets. Conditions: audio generation experiments with limited generated samples. Method (Chung et al., 2025): FAD assumes Gaussian embeddings, which often fail (the paper shows non-Gaussian VGGish embeddings), and its finite-sample bias scales as O(1/N), so FAD decreases as N grows and can be manipulated by changing N. Kernel Audio Distance uses Maximum Mean Discrepancy (distribution-free, unbiased) and the kadtk toolkit. Measured by the authors: on Clotho 2 with N from 100 to 3,839 the FAD deviation roughly halves each time sample size doubles, while KAD stays near its asymptotic value; on DCASE 2023 Task 7 Foley systems, KAD reaches a Spearman correlation of up to -0.93 with human ratings against -0.80 for FAD's best case. Failure modes: KAD has larger variance at small N; music-trained embeddings (MERT, CLAP-laion-music) correlated less well than others on Foley. Limitations: authors' own comparison, Foley sound no...
• articleGiven the structural rules, how should I cut, extend or loop a generated song to a picture duration without breaking phrase structure?
  Problem. Picture is locked to a duration; the generated song is not. Conditions. Pop/rock cue, structure labelled (manually or by an analyser); the generator offers extend/crop (see C3-B575-06). Method (synthesis, mostly inference). 1) Label sections and grid: sections 8-24 bars, phrases 4 bars, hypermeter 4 (C3-B614-01/05). 2) Choose the edit unit: whole sections, or sr/dc halves, never lone phrases (C3-B614-02). 3) To shorten: drop a repeated cycle (e.g. second verse-prechorus) rather than a mid-section phrase; keep the bridge once before the last chorus (C3-B614-03). 4) To lengthen: repeat the final chorus or insert an instrumental cycle, then take the outro (C3-B614-04). 5) Land key hits by shifting tempo or the section, not by squeezing a phrase (see C3-B007-G1-06). 6) Cross-fade at a grid boundary after a fill, and audition both sides. Failure modes: tempo drift and non-integer bar counts in generated audio; lyric lines cut in half. Limitations. Entirely derived from analytic ...
• articleIf I report FAD or CLAP for generated audio, what must I state and why do I still need a listening test? (inference)
  Problem: automatic scores look objective but hide settings. Conditions: any report of FAD, KAD or CLAP score. Method (inference from the round's papers): report the embedding and checkpoint, the reference set, N (number of clips and frames), whether bias was corrected, and the prompt set; do not compare FAD across papers with different embeddings or N; use per-song FAD to find outliers rather than as a verdict; use CLAP score only as a text-adherence proxy and name the checkpoint. Add a listening test with hidden reference and anchors (see C3-B570-15 for MUSHRA) because: original FAD correlated only moderately with human ratings (0.52); VGGish correlated poorly with music quality ratings in the Gui study (n=10 raters); and the human-preference study found model-level metrics can misrank individual models. Also keep automatic MOS predictors in context (C3-B570-14). Failure modes: optimising to a metric (Goodhart); reporting a single number. Limitations: no source gives a minimum N or...
• articleWhat do Netflix's published M&E guidelines say about fill, Foley, stems and file naming, and which of those statements are scripted-specific?
  Netflix's general M&E guideline asks for a fully-filled, long-play, discrete M&E whose levels match the original mix (music untouched, effects changed only as needed to fill) and names files by its sound-asset convention (ME for the master; FXStem, MXStem, DIAStem, FFFXStem for stems; GUIDE for the dialogue guide). It never mentions Foley by name. Foley wording appears on the Nonfiction M&E page (a married music stem plus effects stem when there is no Foley budget) and the Near Field 2.0 page (ambience and Foley fill must match the original mix). So fill is judged against the original mix rather than a fixed checklist (producer interpretation, supported).
• articleHow do I compute a tempo (or a tempo ramp) so that a musical downbeat lands on a given video frame, and what do DAW docs say about doing it?
  Partially verified: the curator re-read none of the cited sources; S8, S10, S9, S7 rest on the producer's pinned reading. Ardour's manual (at the pinned commit) says the preferred way to match tempo to existing material is to drag the beat/bar grid, that snapping a beat to a video frame makes a soundtrack 'punchy and synchronized to the sample', that audio-locked tempo and time-signature markers stay at their frame positions while music-locked ones move, that tempo ramps can be used in a video context for an accelerando by snapping to timecode frames, and that all fractional frame rates are fps x 1000/1001. The manual gives no formula; the arithmetic below is this worker's synthesis: convert the timecode to frames, divide by the exact frame rate to get seconds, then BPM = 60 x beats / seconds for a constant tempo. Worked example: a hit at 00:00:10:12 landing on beat 33 (32 beats after the anchor) is 252 frames = 10.5 s at 24 fps, so about 182.857 BPM; at 23.976 fps the same label is...
• articleHow did silent-film musicians fit music to picture timing in 1920, and what basic practices does the manual give a newcomer?
  Partially verified: the curator re-read none of the cited sources; S7 rests on the producer's pinned reading. Lang and West (1920) describe a workflow of a producer-supplied cue sheet (received about three days to a week before showing) listing numbered cues with minutes, title or description cues, tempo and suggested selections; the player selects music, times the numbers, the main theme and the improvised spaces, and changes music at scene boundaries. Speed of action sets tempo and lighting sets intensity; a flash-back keeps the music's continuity but raises speed and loudness; a climax should be synchronised with a named action (making the climax of a song coincide with the heroine fainting). They advise not to 'crowd the picture' and say a little silence is welcome. Rapee's 1924 Motion Picture Moods was not publicly readable (lending-only), so only this manual was used.
• articleI must voice a cue and do not know the playable range or notation of an orchestral instrument: what do the public-domain treatises give me, and what do the digitised texts fail to give me?
  Partially verified: the curator re-read none of the cited sources; S2, S1 rest on the producer's pinned reading. Forsyth (1914) opens with a reference list of every orchestral instrument's compass in actual sounding pitch plus a 'square note' that shows transposition, and then gives per-instrument written ranges in the body; Berlioz (Clarke/Bennett English text) states compasses per instrument in prose and music examples. In the OCR text that an agent can fetch, the staff-notation compasses are lost, so only compasses stated in words survive; the ranges themselves must be read from the page scans or another machine-readable source. Both treatises treat range as one input to character and balance, not as the whole answer.
• articleWhen and how should sound be planned, from script reading onward, and what artefacts do practitioners say help (questions, memos, sounds played on set)?
  Corrected 2026-10-23 - see C3-B622-02; the original statements below are kept for history and are superseded where the correction says so. Four planning artefacts are documented: (1) script-reading questions that pin down what a character hears and whether the setting has a voice (Thom 2000); (2) an early overall sound concept developed from the finished script (Davis on The Matrix, 1999); (3) designed sounds played on set so actors react (De Bont/Rydstrom on The Haunting, about 100 sounds, two months of prep); (4) a written sound memo that separates realistic source music from sparing underscoring (Welles, 1957-58). The sources also state the usual reality: sound people are typically brought on late, spotting is squeezed, and composer and sound crew rarely coordinate. Planning is therefore a documented best practice on some films, not the norm Weis reports.
• articleWhat can sound do narratively beyond illustrating the picture: how do silence, contrast and recurring sound motifs work, and what do the sources say about using them sparingly?
  Corrected 2026-10-23 - see C3-B622-01; the original statements below are kept for history and are superseded where the correction says so. For a newcomer the sources give three simple, source-named tools. Roles: direct narrative (cueing events), subliminal (emotional colouring) and grammatical (continuity across cuts). Silence: Murch says he used it rarely, citing the end of The Godfather Part II (drop to atmosphere, then nothing) and Welles's held silence in a 1938 radio drama; Weis adds that in dense tracks absence stands out. Motifs: a sound effect tied to a character or idea that prepares the audience for their appearance; Murch's character 'coronas'. All are practitioner or textbook assertions; none comes with audience testing.
• articlelibbw64 (d3dae5c7) rejects audioTrackUIDs longer than 12 characters, caps chna UIDs at 1024 and parses only PCM (formatTag 1) or extensible (0xfffe) format headers (static...
  libbw64 (d3dae5c7) rejects audioTrackUIDs longer than 12 characters, caps chna UIDs at 1024 and parses only PCM (formatTag 1) or extensible (0xfffe) format headers (static reading).
• articleTurning your own recorded sample into a full track (Suno "remix and cover") and why that differs from remixing others' outputs
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mikkel Lassalle (2026-06-30): record a short phrase (a Spanish-style guitar riff; any instrument or voice, even a phone recording), upload it in Suno (Audio > upload, identify audio content), then use "Remix and cover" with a short style prompt ("Spanish guitar", "acoustic ballad"); the result keeps the sample's character ("same DNA"). Rights reading with Suno's current terms (C3-B411-01): uploading material you own is a "Submission" (you keep ownership but grant Suno a broad licence); commercial use of the generated track requires a paid tier and a permitted download; the terms' non-commercial joint-ownership rule applies to "Remixes" made via features that let OTHER u...
• articlestempeg (a41eaabb) code is MIT while its bundled example stem (The Easton Ellises excerpt) is CC BY-NC-SA 3.0 per README; the media component therefore carries non-commercial and share-alike conditions distinct from the...
  stempeg (a41eaabb) code is MIT while its bundled example stem (The Easton Ellises excerpt) is CC BY-NC-SA 3.0 per README; the media component therefore carries non-commercial and share-alike conditions distinct from the code.
• articleOscars rules for films released in 2026 (99th Academy Awards): acting must be "demonstrably performed by humans with their consent", screenplays human-authored, AI use may be investigated - AI in production is not banned outright
  Reported by NPR (2 May 2026) from the Academy's announcement; the official rules PDF was not retrievable (403). Changes for the 99th Oscars: only roles "demonstrably performed by humans with their consent" are eligible for acting awards (excluding synthetic performers such as the AI "actress" Tilly Norwood); screenplays must be "human-authored"; the Academy "reserved the right to investigate the use of generative AI in any submission". The Academy framed AI like earlier technologies (sound, colour, CGI) whose rules evolve; using AI somewhere in production does not by itself disqualify a film (per commentary). Other changes: performers can receive multiple nominations in one acting category; International Feature eligibility widened (festival winners; not limited to one film per country). Practical for AI filmmakers aiming at awards/festivals: keep authorship records (who wrote, who performed, consent forms), expect disclosure questions about generative AI, and keep synthetic perform...
• articleClaims (R6, R7): Sonilo says its music models are "trained only on professionally licensed music, including the Shutterstock catalog", citing a Sonilo-issued 11 May 2026 press release and a Shutterstock LinkedIn post; its SFX training sources are separately described only as "compliant" (not the...
  Claims (R6, R7): Sonilo says its music models are "trained only on professionally licensed music, including the Shutterstock catalog", citing a Sonilo-issued 11 May 2026 press release and a Shutterstock LinkedIn post; its SFX training sources are separately described only as "compliant" (not the same catalogue). R6 itself notes that "Training-source rights and the permission to use generated output are separate." Terms (R5, s6.2): commercial use depends on the plan when the output was generated, and upgrading later does not extend rights to earlier outputs. Free: personal/non-commercial with "Music by Sonilo" credit; Creator (paid): still non-commercial; Pro: commercial including advertising, client work, monetised channels, apps, websites and indie games (under US$200k combined revenue and funding in the preceding 12 months); Premium: adds film, television, broadcast and studio games; Enterprise/API per separate agreement - so the fal listing's "commercial-use-safe" wording does no...
• articleWhat artefacts does Demucs document, and which commonly cited failure modes (phase smearing, vocal remnants) are not in its README?
  Problem. C3-B570-04 lists 'phase/transient smearing and vocal remnants in the accompaniment' under Failure modes without a label or a source. Conditions. Using Demucs for a stem from a mixed track. Method (correction). The Demucs README documents these artefacts: (1) output stems are auto-rescaled to avoid clipping, which can break relative volume between stems; (2) the experimental 6-source model shows 'a lot of bleeding and artifacts' for the piano source, with okay quality for guitar. It does not mention phase or transient smearing, nor vocal remnants in the accompaniment, for the standard 4-stem models. Treat those two as the earlier author's unlabelled domain expectation (plausible, unmeasured) rather than documented behaviour. Failure modes. Reporting undocumented artefacts as the README's. Limitations. README is undated; no model was run. Version/date. README main branch, fetched 2026-10-23.
• articleApart from Baranowski & Hecht, what do open sound-context studies (Ansani et al. 2020; Wiking 2024) report about music or sound changing how a character or a face is judged, and how reliable are they?
  Two open sources add sound-context evidence, neither a neutral-face replication of Baranowski & Hecht. Ansani et al. 2020 (N=118 online, then N=92 in lab) put a 1 min 55 s scene from a short film with a character walking under three soundtracks (melancholic jazz piano, anxious orchestral, ambient control) and found music shifted empathy toward the character, some personality impressions, plot expectations and perceived coziness of the setting, but not the omnibus ratings of the character's affective state (only the single item 'wistful'). Wiking 2024 is a Swedish bachelor thesis with 20 volunteers and open-ended answers to silent versus sound-accompanied face clips; it reports no statistics, its methods text and analysis text disagree in places, and its main observation (child laughter read as irritation or sadness) is anecdotal. An open search found no further open-access experiment that places music under a neutral face (bounded: four OpenAlex queries, top 10 each).
• articleCan you use Suno songs commercially? What the current Terms (effective 3 Sep 2026) actually say
  Primary terms, not legal advice. (1) Paid Pro and Premier: Suno assigns to you its right, title and interest in Output generated from your submissions, but the Output stays subject to the Terms "including any applicable commercial use restrictions", and Suno makes no warranty that copyright vests in any Output. (2) Free or Basic tier: outputs only for lawful, personal, non-commercial purposes. (3) Default rule: no commercial exploitation of the Service, Output or Voice Models except "Permitted Commercial Use": you may commercially exploit Output only if you obtained a permitted DOWNLOAD through an approved channel within your tier's monthly download allocation (shown at suno.com/account and changeable); non-downloaded Output may not be exploited commercially. Commercial rights in obtained Downloads are perpetual and survive later allotment changes. (4) Remixes made via remix features are joint works owned equally with the original creator (where copyright exists) and may only be use...
• articleDAWproject at ee4dcdde models clip fades only as fadeInTime/fadeOutTime with a time unit in Project.xsd, although its README feature table lists Crossfades; Project.xsd contains no timecode/SMPTE/frame-rate concept (curator...
  DAWproject at ee4dcdde models clip fades only as fadeInTime/fadeOutTime with a time unit in Project.xsd, although its README feature table lists Crossfades; Project.xsd contains no timecode/SMPTE/frame-rate concept (curator search).
• articleArtlist MCP connector: searching a licensed music/SFX library and generating media from inside Claude or ChatGPT
  Creator-reported: statements attributed to the creator(s) come from discovery's reading of auto-caption transcript excerpts; the curator checked the video metadata (title, date, length) and any cited documentation pages, not the spoken claims. Nothing was tested; promotional or sponsored framing applies where stated. Mikkel Lassalle (Artlist affiliate, 2026-10-18) shows Artlist's MCP integration: from Artlist's MCP page copy the server URL, in Claude add a custom connector (Settings > Connectors > Add custom connector), log in to Artlist, review tool permissions; then ask in natural language for tracks by mood/genre/BPM/duration or sound effects, play previews inline and open them on Artlist; generation tools (e.g. GPT Image 2 image) ask clarifying questions (aspect ratio, quality) and require per-step approval ("allow once") before spending credits. Practical value: licence-cleared music search without leaving the assistant; approval gating prevents silent credit burn. Unverified: ...
• articleElevenLabs Music: what each plan lets you do with generated songs - no film, TV, radio or studio games below Enterprise Music (terms of 9 Oct 2026)
  Primary terms (Exhibit A). Media Rights for Free, Starter, Creator, Pro, Scale, Business and Enterprise Music Lite: "All online and offline commercial use permitted, except film, TV, radio, and Studio Games"; only Enterprise Music (contact sales) permits all commercial use. So a filmmaker scoring a film or TV piece with Eleven Music needs Enterprise Music. Studio Game vs Indie Game: indie = under $500,000 lifetime game revenue AND the developer/publisher under $1,000,000 annual game revenue (net, incl. affiliates); if a game stops qualifying you have 60 days to upgrade or stop using the output (already-distributed copies may continue). Other table rows: eligibility - Free to Pro individual use only, Scale < 10 employees, Business < 50; monthly generation 11 / 17 / 62 / 304 / 1,100 / 4,800 minutes (Free..Business); monthly downloads not permitted on Free, then 30 / 250 / 500 / 1,500 / 4,000 minutes; streaming distribution prohibited on Free and Starter, permitted from Creator up; mus...
• articleWhich AI music models produce the most preferred songs with vocals? Artificial Analysis vocal board snapshot (23 Oct 2026)
  Closes the open follow-up on the vocal music board (the instrumental board was captured earlier). AA-Music-Vocal v1.1, pairwise human-preference Elo anchored at MiniMax Music 3.0 = 1000, about 2,600-2,800 samples per model, 95% intervals about +/-19-20. Ranking: 1-2 Suno v6 1147 and Suno v6-mini 1130 (statistically tied top pair); 3 Mureka V9.5 1106; 4-6 Mureka V9 1059, Lyria 3 Pro 1051, Lyria 3.5 1051; 7 Eleven Music v2.5 1013; then a tied cluster MiniMax Music 3.0 1000, Eleven Music v2 997, MiniMax Music 2.6 997, Eleven Music 997, MiniMax Music 2.5+ 987; Melodia v3 970. Practical reading: rank ranges matter more than single ranks - the cheaper Suno v6-mini is statistically indistinguishable from Suno v6 here; Lyria 3.5 did not beat Lyria 3 Pro. Preference is not licensing: commercial-use terms and training-data/copyright risk differ by provider (see creator observation of memorised-sounding songs in C3-B393-02) and must be checked separately; prices not captured on this page.
• articleWhat archival assets must a dubbing vendor hand Netflix after the dub mix, and how has that deliverables page changed (its change log)?
  As captured on 2026-03-11, Netflix requires dubbing/AD archival assets within 20 business days of final secondary audio via Source Management, split into Standard and Occasional deliverables; an Atmos dubbed dialogue stem must have at least a 7.1.2 bed and at most 118 objects as long-play 48 kHz/24-bit BWAV ADM; the page change log lists 2020-12-02 and 2023-07-13. The live JSON on 2026-10-22 returned only the introduction, so currency after March 2026 is unconfirmed.
• articleBefore I clean dialogue out of a documentary or reality mix, what does Netflix tell nonfiction partners to deliver as M&E, and what has the page changed since 2020?
  For nonfiction, Netflix recommends Foley (a cloth pass gives substantial fill) and, without a Foley budget, married music and effects stems plus a separate dialogue stem from which its dubbing team builds a faux M&E; the Dialogue Guide is the 5.1/5.0 dialogue stem or its mono mixdown, and optional tracks may be Mono to 7.1.2.
• articleWhat belongs in the body of a Netflix M&E, what goes on optional tracks, what must be delivered for M&E QC, and what changed recently?
  Netflix asks for a fully filled, long-play, discrete-channel M&E; language-specific material (non-dialogue vocalisations, language-specific walla and chants, on-screen TV/radio dialogue) goes on separate Optional Tracks rather than the M&E body; a mix reference video is needed only when the stems are not aligned to the latest locked or final cut.
• articleWhat must I label and how must I build beds and objects when delivering a 5.1 or Atmos mix to Netflix as BWAV ADM?
  Netflix's branded BWAV ADM guideline lets beds and objects be any channel width but requires each to carry a Group label of Dialogue, Music, Effects or Narration (from a published list), true-peak limiting at -2.3 dBFS on material routed to the renderer, and 5.1 stems that sum to the printmaster; BWAV ADM delivery is preferred, not required.
• articleHow does the Universal Category System define CatID and filenames, which version is published, and how do tools carry UCS data in BWF/iXML?
  The UCS site describes UCS as a public-domain initiative and announces version 8.2.1 (January 2024), whose only CatID change corrects WOOD-HANDLE to WOODHndl; the MIT-licensed third-party ucsrename tool (9fa45437) embeds the v8.2 list with 'WOODHandl', builds filenames as CatID_FXName_CreatorID_SourceID_UserData.Extension and rejects underscores in field values. The filename rules come from the tool, not a UCS specification text.
• articleWhich ADM (BS.2076) versions and profiles does the EBU ADM Renderer accept, what is its licence, and how do BS.2125 serial ADM and BS.2127 relate to it?
  At commit 5bb17b42 the EBU ADM Renderer documents BS.2076-1 as its ADM target and, from v2.0, calls itself the reference implementation of BS.2127; files declaring ADM version 2 or later render with a 'not standardised' warning (preliminary BS.2076-2 support is unreleased), serial ADM (BS.2125) is not mentioned in the README, changelog or render command, and the licence is BSD 3-Clause Clear with an explicit exclusion of patent licences.
• articleWhat changed between ATSC A/85:2013 and A/85:2026-07 for dialogue-gated measurement, target loudness, true peak and streaming?
  ATSC A/85:2026-07 keeps the 2013 exchange targets (-24 LKFS with about +/-2 dB, true peak below -2 dBTP) but adds an approximately +/-0.5 dBTP meter tolerance not present in the 2013 section 6, adds Annex L (streaming) and Annex M (one-page summary), and states that BS.1770-3/-4/-5 share identical loudness and true-peak algorithms; Annex M says long-form dialogue level is measured with BS.1770-1 without the relative gate and describes a -23 to -27 LKFS practical range for streaming operators.
• articleWhich loudness measures should I read (integrated, momentary, short-term, range, true peak) and what do the EBU numbers mean?
  Y1-06's R 128 figures match V5 items h), i), m) and it reports +/-0.5 LU only as the V3 history entry; the C2-B80-AUDIT1 grouping of Y1-06 with a +/-0.5 LU non-live claim is incorrect.
• articleFor first-order Ambisonics, what channel order and per-channel gains convert FuMa/B-format (W,X,Y,Z) to ACN/SN3D (ambiX), according to the ambiX paper and the ambix converter, SAF and SPARTA code?
  ambix (24d2875f) and Spatial_Audio_Framework (18fd5aba) both implement first-order FuMa to ACN/SN3D as a W,X,Y,Z -> W,Y,Z,X reorder with W gain sqrt(2) and unit dipole gains (static code reading; not run). The producer's own caveat that these are not independent (shared authorship lineage with the format paper) is retained.
• articleWhat does YuE's MODEL_LICENSE (YuE2) say clause by clause about hosting, redistribution, modification, training and output use of the weights, and what do THIRD_PARTY_NOTICES add?
  At YuE 1647252d, MODEL_LICENSE licenses the three YuE2 checkpoints under CC BY-NC 4.0 with a dated (2026-09-16) additional permission for individual creators to generate and monetise outputs under responsible-use conditions; it excludes code/tokenizer/evaluation assets from its scope, denies commercial redistribution or sale of weights, and directs companies to a commercial licence. This fills the MODEL_LICENSE gap recorded by L07 for C2-B04-H-12.
• articleIs YouTube Audio Library music safe from Content ID claims, and what attribution does it require?
  Problem: choose background music for a YouTube video without claims. Conditions: tracks and effects from YouTube Studio's Audio Library (help page fetched 23 Oct 2026). Method: Audio Library items are described as royalty-free production music and sound effects that are copyright-safe: tracks downloaded from it will not be claimed by a rights holder through Content ID, and Partner Program channels can monetise videos that use them. Attribution: if a track has a Creative Commons licence, you must credit the artist in the video description (Studio generates the text; filter 'Attribution required' / 'Attribution not required'); videos with Audio Library music show a 'Music in this Video' section, and CC attribution is still required in the description. Limits: only Audio Library items are known to YouTube to be copyright-safe; YouTube is not responsible for issues with 'royalty-free' music from channels or other libraries; it cannot give legal guidance; the library is only in YouTube S...

More