Music and sound design

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

• articleWhat true-peak and loudness limits do Netflix's public sound specifications state for a Music and Effects (M&E) mix?
  In the Netflix Sound Mix Specifications v1.6 (archived 9 Aug 2026), the 5.1 M&E section states no numeric peak or loudness value of its own; M&E peak compliance is by reference to the Netflix Peak specification, -2.3 dBFS limiter settings are recommendations, and the theatrical 0 dB true-peak allowance belongs to a different deliverable.
• articleIf I put happy or sad music under a close-up of a neutral face, will viewers read the face differently, and what should I check first?
  One experiment tests exactly this: in Baranowski's study (30 students, thesis chapter and journal abstract), happy music made actors look happier and sad music less happy, with the effect strongest when the face itself was neutral; sad music did not make faces significantly sadder than no music. A different open study (Ansani et al. 2020) found music changed empathy and impressions of a character but not the overall attributed emotional state. No independent replication with a neutral face was found in the open sources checked. So music can be expected to push reading in its own direction, modestly, and the no-music version is the baseline to compare against. The sources do not say who owns the music used, so clearance is a separate step.
• articleWhich parts of the wayang kulit night structure do the sources treat as fixed and which as flexible, what is pathet as a musical-narrative device, and what are the transfer limits for contemporary large-scale pacing?
  A study of a Klaten (Jombor) Bratayuda performance finds the division into three pathet is the part of the pattern followed strictly, while the internal order of jejer, adegan and perang is flexible: a jejer may be followed by adegan but no battle, by battle only, or by scenes that continue in a different pathet; scene description may be absent; sulukan, gending and cue sounds are used as needed. A 2004-2009 Surakarta programme study found three kinds of structure: the old pattern, compact (padat) staging that ignores the pathet sequence, and structures not following the usual order. Sumarsam's paper shows pathet itself has been defined many ways (e.g. as the dalang's singing, by gendèr tuning, by melodic patterns), and that the names nem, sanga and manyura lack an agreed explanation. For a contemporary storyteller this supports adopting 'three mode-defined blocks with a repeating internal micro-structure' as a proposal only.
• articleIs there an official, citable Universal Category System filename specification (PDF or HTML at a dated version) that I can fetch from the UCS site, or must I rely on tools and vendor pages?
  Negative result at the public-web level. At access time the official site (universalcategorysystem.com) publishes no filename-specification PDF or HTML page itself: it links only to resources.universalcategorysystem.com, which redirects into a Dropbox shared folder whose download form is a single 339,633,132-byte 'UCS Release.zip'. The folder listing could not be read without downloading the archive or running JavaScript, so whether a dated filename-spec document exists inside it is unverified. The site's version note is 8.2.1 (January 2024); earlier captures show the repository was Google Drive in 2020 and Dropbox by mid-2023.
• articleHow is a UCS sound-effects filename built (CatID, FXName, CreatorID, SourceID, UserData), which fields are required, and what do open tools say about the separators?
  Two independent open tools describe the same layout, CatID_FXName_CreatorID_SourceID_UserData, with the underscore as the block separator. They disagree on strictness: ucsrename (README) calls CatID, FXName, CreatorID and SourceID required with UserData optional, while ucs-tools (code docstring) says only a valid CatID at the head is a hard requirement. Neither is the UCS specification; the official filename text was not reachable. ucs-tools additionally documents optional '-UserCategory' after CatID and 'VendorCategory-' before FXName.
• articleWhen voicing a cue for orchestra, which doubling, balance and dynamic techniques do Berlioz and Forsyth give, where do they disagree or qualify, and what transfers to a sampled or virtual orchestra?
  The two treatises converge on concrete, checkable rules. For energy in the strings, double first violins by second violins in unison rather than an octave lower unless the line lies very high (Berlioz); do not add violas in octaves beneath unison violins, use the violas to reinforce the cellos in unison instead (Berlioz); keep cellos with basses unless a strong effect is planned (Berlioz); do not double a trombone bass theme with bassoons, cellos and basses (Berlioz via R. Strauss's annotation, quoted by Forsyth). Forsyth adds the numerical logic of balance: dividing a part halves the players and their dynamic efficiency; second violins seated with f-holes turned away count for about half the firsts; and unequal 'telling' power breaks contrapuntal balance in older scores. Neither treatise addresses samples; the transfer to sampled orchestras is synthesis and testable.
• articleOf the free sound-effects libraries I might use (Freesound, Sonniss GDC bundle, BBC Sound Effects, Pixabay sound effects), which say anything about AI or machine-learning training, in which document, and does the short summary page say the same as the legal text?
  A comparison at dated reads. Freesound: training allowed if each sound's CC licence is respected, plus uploader preferences since July 2026. Sonniss: AI training expressly prohibited in the licence and repeated on the bundle page. BBC: AI development or training needs BBC permission. Pixabay: the licence summary page says nothing about machine learning, while the Terms of Service prohibit scraping and data mining "for machine learning purposes" and describe a contributor opt-out for Pixabay's own AI training; so a reader of the summary alone would miss the ML clause. Mixkit's sound-effects licence text is script-rendered and was not obtained.
• articleWhat does the Sonniss #GameAudioGDC bundle licence (version 2.0, effective 27 August 2026) permit and forbid for commercial use, redistribution, attribution and AI training, how did it change, and where does the bundle page summary differ from the legal text?
  At the snapshot of 2026-10-10 the licence version 2.0 allows use and modification in personal and commercial projects without attribution, bars selling the sounds as they come and bars supplying them to others as sound effects (also in libraries or packs, modified or not), and expressly prohibits using them to train, develop or enhance AI technologies. The history page says the AI section was added on 28 January 2024, that earlier text allowed free distribution, and that the version published on the download day governs. The bundle page summarises the sounds as licensed for media production "only" and the AI ban as "training", both narrower or different in wording than the legal text.
• articleCan I use sound generated by MMAudio, HunyuanVideo-Foley or ThinkSound in a commercial delivery, according to what their licences and cards actually say?
  The texts differ per component. MMAudio: code MIT; checkpoints CC BY-NC 4.0 (non-commercial) with a README warning that training-dataset licences apply and commercial suitability is not guaranteed. HunyuanVideo-Foley: Tencent Hunyuan Community License, which says Tencent claims no rights in Outputs but excludes EU/UK/South Korea, bars using Outputs to improve other AI models, restricts use outside the Territory and adds a 100M monthly-active-user condition. ThinkSound: HF card says Apache-2.0 while the GitHub README says commercial use is not permitted (see -05). No text read grants clearance; this record does not conclude legal permission.
• articleWhat goes wrong with temp tracks ('temp love'), what mitigations do editors and composers describe, and where do sources disagree?
  Practitioner sources agree temp music shapes the final score: Carlson hears 'the DNA of the temp' in many scores, and Harrison says composers end up with a 'sideways version'. They differ on remedy and value: Harrison treats temp love as a curse or a help (non-musical filmmakers can say what they love in the temp), while the Pluribus editors (Art of the Cut) avoid temp except for montages and one temp-scored first episode shown to the studio. A blog post under Randy Thom's name overstates the editors' own words ('the entire series without any temporary score'): the interview says exceptions existed, so the blog is a lead, not evidence of the claim.
• articleWhat is the Universal Category System for sound effects, where is its official list published, which version and category list does it define, and under what terms?
  UCS describes itself as a public-domain initiative offering a fixed category list and a filename structure for sound effects; its site (observed 2026-10-22) announces version 8.2.1 (January 2024). Its only distribution channel is a Dropbox shared folder reached through resources.universalcategorysystem.com, which a raw HTTP read cannot list, so no official specification text or official CSV was read at a stable URL. The 8.2.1 list can be read as plain CSV from three third-party repositories (each citing the UCS site as source): 753 CatID rows, 82 categories, columns Category, SubCategory, CatID, CatShort, Explanations, Synonyms. Terms are a self-description ('public domain'), not licence prose.
• articleDid Wagner call his recurring themes 'leitmotifs', who did, and what did he call them?
  In Ellis's English translations, Wagner's own accounts (1851 'A Communication to My Friends'; 1879 'On the Application of Music to the Drama') describe a 'tissue' or 'web' of 'thematic Motivs', 'root-themes' and 'chief-moods'; the only place the word Leitmotive appears in the volumes inspected is in the 1879 essay, in quotation marks, attributed to his younger friend Hans von Wolzogen ('what he calls my Leitmotive'). Ellis's Vol. II translator's preface also uses a word the OCR renders 'leitmotivtn' (read as leitmotiv-) as a metaphor for recurring words, not for music. Within these texts, the term is therefore Wolzogen's name for the phenomenon that Wagner himself describes differently. Whether Wolzogen first coined the word, or someone else, was not established.
• articleHow does MIDI-CI v1.2 stay compatible with MIDI 1.0 devices, and what happened to Protocol Negotiation?
  MIDI-CI v1.2 keeps MIDI 1.0 devices working (backward compatibility as a design goal; messages travel as Universal System Exclusive) and, in version 1.2 (2023-06-15), deprecated Protocol Negotiation while adding Process Inquiry and Function Blocks.
• articleWhat is a MIDI Clip File (.midi2), how is song-level information such as tempo, key, lyrics and names stored in it, and does it carry notation?
  A MIDI Clip File (.midi2) is the MIDI 2.0 counterpart of a Type 0 SMF: an 8-byte 'SMF2CLIP' header followed only by Universal MIDI Packet messages; tempo, time/key signatures, names, copyright and lyrics that were SMF meta events are now UMP messages (many as Flex Data text, per producer reading of M2-104).
• articleWhat terms do MedleyDB and FMA state for their audio, annotations and metadata, and do they address model training?
  MedleyDB's pages offer the dataset for non-commercial research under Creative Commons (named both as Attribution-NonCommercial and as BY-NC-SA 4.0) and ask users not to republish without consent; the Zenodo audio record (v1.0) is access-restricted with no licence field and points to a GitHub repository for annotations whose LICENSE is MIT, while the description page says audio and annotations are released under BY-NC-SA. FMA separates MIT code, CC BY 4.0 metadata and per-artist audio licences, for research purposes. Neither text addresses model training.
• articleDawDreamer docs at e0daff3c state both that automation granularity is the block size and that automation data is interpreted at audio rate; the render loop calls automateParameters once per block with the buffer size, consistent with block-wise application (interpolation code not...
  DawDreamer docs at e0daff3c state both that automation granularity is the block size and that automation data is interpreted at audio rate; the render loop calls automateParameters once per block with the buffer size, consistent with block-wise application (interpolation code not read).
• articleWhat do Freesound's per-sound Creative Commons licences, attribution guidance and AI-training answers say at the access date, and where does Freesound's own summary go beyond or differ from the Creative Commons legal texts?
  Freesound distributes each sound under the licence its uploader chose (CC0, CC BY or CC BY-NC 4.0, plus legacy Sampling+). Its FAQ now answers AI training as "yes as long as individual sounds' Creative Commons licenses are respected" and, as of July 2026, adds uploader-level Gen AI preferences (open-source-only, non-commercial open-source-only, no generative AI, and a voice opt-out) on top of the licence, exposed to API users for filtering and in Data Packs. Freesound labels its CC-to-training reading as its own interpretation (for example CC-BY requires disclosing the training set); the CC legal code text does not mention AI and the CC FAQ says the answer depends.
• articleThe BBC Sound Effects archive says it is free to download: what does the RemArc licence text actually permit (personal, research, education, commercial), what must I do, and what does it say about text and data mining or AI?
  The BBC Sound Effects site is a script-rendered app whose licence text is embedded in its JavaScript bundle (read as text only). That text (the BBC's Content Licence for RemArc) permits non-commercial, personal or research use and formal education use by students and staff, requires a credit, bars sharing such as uploading to social media, and says text and data mining, computer analysis, or developing or training AI need BBC permission and may cost a fee. Commercial use is routed to Pro Sound Effects; metadata is under the Open Government Licence v3.
• articleAt the mix-to-delivery handoff, which stem, M&E and track-layout rules do Netflix v1.4, EBU R 123 and AS-11 state, and what does the receiver still not get?
  P2-04's statement that role labelling is positional (track number) holds for AS-11 UK DPP HD; for X-series files MCA labels carry roles (CA-B066 C2-03 reading).
• articlepedalboard v0.9.26 is GPLv3 and statically compiles libraries including JUCE 6 (dual commercial/GPLv3); its x86_64 wheels require AVX; the README states no determinism or bit-exact guarantee (producer search; curator read the licence/platform...
  pedalboard v0.9.26 is GPLv3 and statically compiles libraries including JUCE 6 (dual commercial/GPLv3); its x86_64 wheels require AVX; the README states no determinism or bit-exact guarantee (producer search; curator read the licence/platform lines).
• articleWhat do ASCAP, BMI, SOCAN and PRS for Music publicly say about AI-generated music in registration, and do library pages say anything about it?
  A joint release dated 2025-10-28 (hosted on SOCAN's site) says ASCAP, BMI and SOCAN each adopted policies to accept registrations of partially AI-generated compositions, defined as combining AI-generated musical content with human authorship, and that entirely AI-created compositions are not eligible. BMI (403), ASCAP's own AI help page (403) and a PRS AI policy PDF (404 at the URL a search returned) could not be read, so the societies' own policy texts and PRS's position are not inspected here. None of the library, publisher or Guild pages read contains any AI statement. The release says nothing about cue sheets, clearance or licensing of AI-made music.
• articleHow do DistroKid, TuneCore and CD Baby treat AI-generated or AI-assisted music at upload: do they accept it, ask for a disclosure, or exclude it?
  Three different models appear in the Help Center text read on 2026-10-22. DistroKid accepts AI-tool music on rights and impersonation conditions and asks at track upload whether any of it was AI-generated (lyrics, music, all of the audio, part of the audio; an "All of the audio" answer triggers a human-or-AI-persona question; credits can be edited later; pure tool use such as pitch correction or AI-assisted mastering needs no credit). TuneCore distributes AI-assisted music only if every GenAI tool used was trained on fully licensed datasets, and its publishing arm says it runs AI detection and that songs flagged as likely AI-generated may not be processed. CD Baby says it cannot accept any AI-generated content, even partly, and will remove it and possibly end the relationship. The three differ on whether the gate is a disclosure (DistroKid), a tool-provenance rule (TuneCore) or exclusion (CD Baby). Access note: the HTML pages returned a bot challenge to curl; the public Help Center ...
• articleWhat does Deezer do about AI-generated music (detect, tag, exclude, demonetise, remove), what can an uploader declare, and where do Deezer's own pages contradict each other?
  Across five Deezer press releases (2025-06-20, 2026-01-29, 2026-04-20, 2026-07-21, 2026-10-13), Deezer describes platform-side detection of fully AI-generated tracks (its own patent-pending tool, claimed to detect output of named generators), a listener-visible tag on albums that contain such tracks, automatic exclusion from algorithmic and editorial recommendations, demonetising of streams judged fraudulent, no longer storing hi-res versions (April 2026), a July 2026 takedown rule for fraud-linked tracks and tracks unstreamed for six months, and an announced listener toggle "before the end of 2026". No uploader-side AI disclosure field is described in these pages. All figures are Deezer's own. The July 2026 release dates the first tagging to June 2026 in one place and June 2025 in another, and keeps a notes-to-editors paragraph calling removal or demonetising "potential future actions" in the same release that announces takedowns.
• articleWhich DDEX ERN 4.3.2 elements and values carry an AI-generated flag for a release, recording or contributor, and how do YouTube, Spotify and DistroKid disclosures relate to them?
  In the ERN 4.3.2 XSD (Last-Modified 2025-06-30), a three-valued ContainsAI element (All / None / Partly, defined in the allowed-value-sets file) appears on Release, SoundRecording, Image, Text and Video, and a contributor-level AiContribution element appears on Contributor and EditionContributor, defaulting to All when SpecialContributor is GenerativeAI. Documented consistency rules: if a resource-level value is All only GenerativeAI contributors may be listed; if None no contributor may carry Partly or All. The release notes list recording-level and contribution-level AI communication under the Version 4.3.1 entry. YouTube accepts the declaration via DDEX ERN 4.3.2+ or a CSV column (all/partly/none/unknown) and reads a missing value as unknown. Spotify's provider page describes role-level credits for roles that were fully AI-generated, in a beta; DistroKid asks about lyrics, music, all of the audio or part of the audio. Which DDEX value a distributor writes for a given UI answer is...
• articleDo YouTube's public Content ID pages say anything about AI-generated music or video as reference material, and how does the separate music-partner AI declaration relate to Content ID?
  Negative result, scoped to the two pages read (S3 "Content eligible for Content ID" and S4 "Qualify for Content ID", captured 2026-10-22): neither contains the words AI, artificial, generative, synthetic or machine-generated (0 hits each after whitespace normalisation), so they state no AI-specific eligibility rule. Eligibility turns on exclusive rights, distinct individual references, and manual review for content sold or licensed at scale; open-licence and non-exclusive material is ineligible, as are sound effects and loops. YouTube's AI declaration for music partners (page S2) is a separate mechanism, delivered via DDEX or CSV, and that page does not mention Content ID (0 hits). Whether a given AI-generated track can satisfy "exclusive rights" depends on facts these pages do not address, such as the generator's output terms (see C3-B138-G49 for one service's terms). No legal conclusion is drawn. The Content ID partner agreement and CMS templates are not public and were not read.
• articleDoes DDEX's own Knowledge Base or implementation guidance say anything about populating ContainsAI or AiContribution beyond the schema and Data Dictionary, and where do DDEX's own documents disagree or stay silent?
  Scoped negative: in the Knowledge Base navigation (about 400 article titles, page last-modified 2026-10-06), in 14 targeted KB articles and in the ERN Part 1 sections read, no DDEX implementation guidance on populating ContainsAI or AiContribution was found; the AI fields appear only in the release-notes annex, the Data Dictionary and the value set. Within those, the Data Dictionary describes ContainsAI as a true/false Flag while the value set is three-valued (All / Partly / None); the Release-level row states no consistency rule; and DDEX's "unknown" convention (#unknown#) is for mandatory elements, so it does not supply the "unknown" value that YouTube's CSV accepts. These are observations of silence and wording, not defects proven in the standard.
• articleWhat does Deezer tell distributors and other business partners about using its AI-detection output (what is detected, who decides the consequences, what uploader declarations count), and is a supplier-facing AI delivery policy published?
  Deezer for Business's AI Detection FAQ (system dates created 2026-05-12, updated 2026-05-21) is addressed to distributors, rights holders, collecting societies and platforms who might license the detector. It says the tool classifies and tags, that consequences (exclusion, demonetising, labels, royalty treatment) are each partner's decision under their own policies, that detection reads audio patterns rather than metadata or uploader declarations, that it focuses on fully AI-generated tracks with hybrid detection "in active development", and gives company figures (39% of deliveries, up to 85% of that fraudulent, false-positive rate below 0.01%). No supplier-facing delivery policy on AI was found in the 16 business help-centre articles; so a distributor's own AI rule, not a Deezer supplier rule, is what an uploader can read.
• articleWhat should a dialogue editor check on AI-cleaned dialogue before delivery, given the failure modes and behaviours that vendor pages, repositories and papers actually document?
  No source read provides a delivery checklist for AI-cleaned dialogue, so this candidate assembles one from documented behaviours and labels each check as a proposal. The documented behaviours cover timing (STFT delay, chunk re-alignment, export drift, export parity), format (mono downmix, 44.1/48 kHz), level (normalisation, rescaling), over-processing (artifacts, silent waveforms, unprocessed syllables), breath leakage, word changes in generative enhancement, tool-version defects and where the audio is processed. Room tone and ADR conventions, and disclosure of AI use to a client, are covered by other batches.
• articleFor the open models people name for dialogue cleanup (DeepFilterNet, Resemble Enhance, Demucs/HTDemucs), what inputs, outputs, controls and sync/level behaviour do their repositories document or imply, what do they actually claim about dialogue, and what are the per-component licences?
  At pinned commits: DeepFilterNet is a 48 kHz real-time noise suppressor whose Python CLI compensates its STFT delay by default while the Rust binary only does so with -D; Resemble Enhance averages to mono, works at 44.1 kHz, processes long audio in overlapping 30 s chunks with per-chunk peak normalisation and cross-correlation re-alignment, and is described as also restoring distortions and extending bandwidth; Demucs documents music stems only and its README (searched) never mentions speech or dialogue, so "Demucs for dialogue" is not a documented use. The Cocktail Fork paper is the film-relevant separation reference, but evaluates on synthetic single-channel mixes. Code licences are stated (MIT, or MIT/Apache-2.0); weights licences are stated only for Resemble (card says MIT), not DeepFilterNet or Demucs.
• articleWhich Google media generation models are listed in the Gemini API today (video, image, music), and is Veo among them?
  Gemini API models page (re-fetched 2026-10-23 ~11:35Z): media generation entries include Gemini Omni Flash (gemini-omni-1.1-flash) for video generation/editing/interpolation/extension; Nano Banana family for images (C3-B383-01); Imagen 4 marked "Shut down"; music: Lyria 3.5 (lyria-3.5, flagship full-length songs), Lyria 3 Clip (lyria-3-clip-preview, clips/loops up to 30 s), Lyria 3 Pro (lyria-3-pro-preview, previous generation) and Lyria RealTime (lyria-realtime-exp, streaming with granular control). A text search of the page found no "Veo" entry (negative check; Veo may still be offered via Vertex AI, Flow, Vids or YouTube, which were not checked here). Combined with OpenAI's Sora 2 API shutdown on 2026-09-24 "with no one-to-one replacement API" (addendum to C3-B385-01), this shows frontier video APIs are being consolidated or withdrawn; tutorials built on Veo-in-Gemini-API or Sora API calls may be outdated. Creator use of Veo 3.1 via Google Vids (C3-B344-04) is a consumer route, n...
• articleWhat should an agent check before placing AI-generated music in a film, game or ad?
  Synthesis from the five service/model reads: (1) which text and date you relied on; (2) plan tier at generation; (3) permitted-download or export status; (4) medium restrictions (film/TV/radio/games); (5) attribution; (6) provenance marks left intact and any platform AI-disclosure rules; (7) prompts avoided artist/song/lyric names; (8) human contribution documented for any copyright claim; (9) component licences for open models; (10) a human owner of the final clearance. The US Copyright Office report (Jan 2025) says prompts alone do not make users authors; the services disclaim or limit copyright vesting. This is not legal advice.
• articleCan AI-generated images, video or music be copyrighted in the US, and does prompting count as authorship?
  U.S. Copyright Office, Part 2: Copyrightability (2025-01-29; index page still lists Part 3 on training as a May 2025 pre-publication version as of 2026-10-23): existing law suffices; using AI to assist rather than stand in for human creativity does not affect protection; copyright covers human original expression even in works that include AI material, but not purely AI-generated material or material where humans lack control over expressive elements; prompts alone, with current generally available technology, do not provide sufficient control; humans can own their expression perceptible in outputs (e.g. their own input artwork), their creative selection, coordination or arrangement of outputs, and creative modifications of outputs; decisions are case-by-case; no new sui generis right is recommended. Practical: document human contributions (input artwork, edits, compositing, sequencing) and disclaim AI-only portions when registering; this aligns with studio practice requiring human ...
• articleCan I compare reported DeSync and IB-score numbers across Kling-Foley, HunyuanVideo-Foley, MMAudio, V-AURA and world-model audio papers, and what do real recordings score?
  Only partly. The same system gets different numbers in different papers: V-AURA is 155 ms in its own paper (2.56 s clips), 0.654 s in MMAudio (8 s, two 4.8 s crops), 0.72 s and 0.86 s in HunyuanVideo-Foley's tables, and 1.287 s in WorldSonus (5 s clips). Kling-Foley reuses MMAudio's baseline rows but reports an MMAudio row (IB 29.26, DeSync 0.45) that matches none of MMAudio's four published rows, and its abstract claims best distribution matching while its own Table 2 shows MMAudio ahead on FD and KL. HunyuanVideo-Foley's own VGGSound-Test table has MMAudio at lower DeSync (0.47) than itself (0.53). The only ground-truth reference found is Foley-Omni's V2ST-Bench, where real recorded audio scores DeSync 0.14.
• articleWhen a paper says its audio is "in sync", what do DeSync, IB-score, AV-Align and the human scores actually measure, and how is each computed?
  Five different things are called "synchronization" in the sources. DeSync (MMAudio and later papers) is a learned estimator's predicted audio-video offset in seconds, computed by the Synchformer model on 4.8 s windows. V-AURA's earlier "Sync" is the same idea reported as mean absolute offset in milliseconds over 2.56 s clips. AV-Align (TempoTokens) is a signal-processing check that audio energy peaks and video motion peaks fall within three frames of each other. MMAudio also reports a model-free onset accuracy on Greatest Hits. Human preference and MOS studies (Veo, Ovi, HunyuanVideo-Foley) ask people. IB-score is not a timing metric: it is semantic similarity.
• articleDo interactive world models make sound today, and which audio-capable ones are only a paper, a demo, or something I can actually download?
  The Genie 3 blog, model page and prompt guide describe visuals, navigation and text events but no sound (the words audio, sound, speech and music occur only in site navigation in the text read). Veo 3 and 3.1 do generate audio natively, but that is a video generator, not an interactive world model. Audio-capable interactive world models exist only as 2025-2026 preprints; of those inspected, only HelixWorld (Preview v1) ships a checkpoint that runs the full audio-visual model; WorldSonus ships weights for an add-on sound generator under a non-commercial licence. All performance numbers are the authors' own.
• articleFor open music/audio models (Stable Audio Open, MusicGen), what do code, weights, training data and outputs each permit?
  Components differ. Stable Audio Open 1.0 and Small: code in stable-audio-tools is MIT; weights are gated on Hugging Face and the public card names the Stability AI Community License (commercial registration, revenue threshold, attribution) with output ownership stated 'as between' Stability and the user; training data are stated as CC0, CC BY or CC Sampling+ audio with content-detection screening. MusicGen (AudioCraft at commit 896ec7c47f5e5d1e5aa1e4b260c4405328bf009d): code MIT, weights CC BY-NC 4.0, training data stated as licensed (Meta Music Initiative, Shutterstock, Pond5). Both model cards say they should not be used downstream without further risk evaluation. SAO's own card says vocals are not realistic and MusicGen's says the same.
• articleWhich TTS voices and music models lead blind preference tests in Oct 2026, and at what API price?
  Artificial Analysis Speech Arena, provider-voice board (rendered 2026-10-23): Eleven v4 Turbo 1335 (+/-17; Sept 2026; $40/1M chars), Eleven v4 1329 ($80), Qwen-Audio-3.1-TTS-Plus 1301 ($19.3), Sonic 3.6 1289 (Aug 2026; $49), Gemini 3.8 Flash TTS 1278 ($16.5), Realtime TTS-2 1267 ($20.8), Qwen-Audio-3.0-TTS-Plus 1265, Gemini 3.8 Flash-Lite TTS 1251 ($11), Fish Audio Drama 3 Preview 1248 (Oct 2026; $15), Simba 3.2 1245 ($6.6), Voxtral 3 TTS 1218 ($13); ~2,000-3,400 samples each, 8 voices per model. AA-Music-Instrumental v1.1 (anchor MiniMax Music 3.0 = 1000): Suno v6 1148 (+/-22), Suno v6-mini 1114, Mureka V9.5 1084, Mureka V9 1083, Lyria 3 Pro 1080, Lyria 3.5 1078, Eleven Music 1021, Stable Audio 3 Large 1014, Eleven Music v2 1011, MiniMax Music 2.5+ 1007, ..., Lyria 2 926, MusicGen 868 (~2,100-2,300 samples each; separate vocal board exists, not captured). Use: price/quality trade-offs are large (e.g. Gemini 3.8 Flash TTS within ~57 Elo of Eleven v4 at about a fifth of the price); F...
• articleIf I deliver AI-generated music to Deezer through a distributor, what do Deezer's own help pages say will happen to it, is there anything I declare, and what can I do about a wrong tag?
  Deezer publishes one artist-facing help article (Deezer for Creators, system dates created 2025-11-10, edited 2026-03-29, updated 2026-07-23) beyond its newsroom: detection and tagging run automatically at upload, tagging is mandatory, tagged tracks "may be excluded" from algorithmic recommendations (and, in an FAQ of the same article, "are excluded"), royalties are described as unchanged, and a wrong tag is appealed through the distributor first, then a support ticket after 5 business days. No uploader declaration field is described; artists are only encouraged to be transparent. The tagging scope is stated two ways in the same article (tool use or significant AI elements versus primarily fully AI-generated tracks). A separate supplier or delivery policy on AI was not found in the 21-article creator help centre, the 16-article business help centre or the consumer terms.
• articleWhat do primary sources fix for AmbiX (ACN/SN3D), YouTube spatial-audio uploads and Opus ambisonics, and what breaks if FuMa material is mislabelled?
  YouTube's spatial-audio help requires AmbiX (ACN ordering, SN3D normalisation) with first-order audio as a single 4-channel W, Y, Z, X track at 48 kHz (PCM in MOV, AAC at 256 kbps or more, or Opus family 2 at 512 kbps or more in MP4), plus a 6-channel head-locked variant; Google's SA3D box declares ordering and normalisation and uses channel_map to describe a track's order (W,X,Y,Z input -> 0,2,3,1); RFC 8486 Opus family 2 carries ACN-ordered, SN3D-normalised channels with optional non-diegetic stereo.
• sourceHunyuanVideo-Foley
• sourcestable-audio-tools
• sourcePedalboard
• sourceBasic Pitch (audio-to-MIDI)
• sourceYuE / YuE2
• sourceMMAudio (video-to-audio synthesis, CVPR 2025)
• sourceCLAP (CLever Audio Plug-in API)
• sourceAudioCraft (MusicGen, AudioGen, EnCodec)
• sourceSpleeter
• sourceDiffRhythm
• sourceDemucs (maintained v4 line)

More