{"id":"e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17","title":"Phonon TTS: the authors’ case for speech generation on your own device","argument":"Phonon’s authors—Olesia Krizhevich, Laurent Mazare, Eric Bezzam and Eustache Le Bihan—describe a small text-to-speech model designed to run on a user’s device without a server or network. They argue that this keeps typed text on the device while making speech generation available offline. The authors say the release includes models of about 65 MB and 75 MB, covering English, French, German, Spanish and Portuguese, with more than 100 built-in voices. Licensing differs: Phonon 31m is Apache 2.0, while the other models are CC BY-NC. The authors report that Phonon ranks first for intelligibility in German and Spanish and in the top three in every language they evaluated; they also say it tops the CPU streaming benchmark for time-to-first audio. The article also describes demonstrations on devices including an Apple Watch and iPhone, and says Phonon was downloaded more than 200,000 times in its first two weeks. The authors present offline operation, small models and adaptable voices as the release’s central features, while noting that additional languages and custom models can be developed with design partners.","topicIds":["intelligence-and-discovery","work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The article is written by the model’s creators and presents their account of its features, adoption and leaderboard performance. Escape Meridian interpretation: the article’s reported leaderboard rankings do not establish performance across all devices or real-world uses. The article describes demonstrations and leaderboard results but does not report comparative measurements of performance across the listed device types.","speaker":{"name":"Olesia Krizhevich, Laurent Mazare, Eric Bezzam, Eustache Le Bihan","roleAtSource":"Article author"},"source":{"title":"A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.","publisher":"Hugging Face","format":"Article","url":"https://huggingface.co/blog/phonon-tts","publishedAt":"2026-11-05T00:00:00.765Z","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"The authors describe Phonon as a text-to-speech model that runs on a user’s device without a server or network.","excerpt":"our small text-to-speech model that runs on your own device. It needs no server and no network","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors say the two models are about 65 MB and 75 MB and together cover five named languages.","excerpt":"Phonon comes in two sizes, at about 65 MB and 75 MB. Together they speak English, French, German, Spanish and Portuguese.","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors report first-place intelligibility rankings in German and Spanish, and top-three rankings in every language evaluated.","excerpt":"On intelligibility, Phonon ranks first in German and Spanish, and in the top three in every language we evaluated","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors report that Phonon topped the CPU streaming benchmark for time-to-first audio.","excerpt":"Speed is where we see Phonon truly shine, as the models top the CPU streaming benchmark on time-to-first audio.","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors say Phonon 31m uses Apache 2.0, while the other models use CC BY-NC licenses.","excerpt":"Phonon 31m is Apache 2.0, so you can use it for free, even in a commercial product. The other models are CC BY-NC","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors report more than 200,000 downloads in the first two weeks after launch.","excerpt":"Phonon was downloaded more than 200,000 times in its first two weeks","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"}],"sourceMedia":{"status":"found","sourceUrl":"https://huggingface.co/blog/phonon-tts","checkedAt":"2026-11-10T04:48:07.073Z","items":[],"note":"Media was declared by the source, but no asset passed the supported availability checks. Open the original source to view it."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do Phonon’s speed and intelligibility results vary across the different devices on which the authors say it runs?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Phonon TTS: the authors’ case for speech generation on your own device","summary":"Phonon’s authors—Olesia Krizhevich, Laurent Mazare, Eric Bezzam and Eustache Le Bihan—describe a small text-to-speech model designed to run on a user’s device without a server or network. They argue that this keeps typed text on the device while making speech generation available offline. The authors say the release includes models of about 65 MB and 75 MB, covering English, French, German, Spanish and Portuguese, with more than 100 built-in voices. Licensing differs: Phonon 31m is Apache 2.0, while the other models are CC BY-NC. The authors report that Phonon ranks first for intelligibility in German and Spanish and in the top three in every language they evaluated; they also say it tops the CPU streaming benchmark for time-to-first audio. The article also describes demonstrations on devices including an Apple Watch and iPhone, and says Phonon was downloaded more than 200,000 times in its first two weeks. The authors present offline operation, small models and adaptable voices as the release’s central features, while noting that additional languages and custom models can be developed with design partners.","question":"How do Phonon’s speed and intelligibility results vary across the different devices on which the authors say it runs?","claims":[{"text":"The authors describe Phonon as a text-to-speech model that runs on a user’s device without a server or network.","excerpt":"our small text-to-speech model that runs on your own device. It needs no server and no network","support":"source-stated"},{"text":"The authors say the two models are about 65 MB and 75 MB and together cover five named languages.","excerpt":"Phonon comes in two sizes, at about 65 MB and 75 MB. Together they speak English, French, German, Spanish and Portuguese.","support":"source-stated"},{"text":"The authors report first-place intelligibility rankings in German and Spanish, and top-three rankings in every language evaluated.","excerpt":"On intelligibility, Phonon ranks first in German and Spanish, and in the top three in every language we evaluated","support":"source-stated"},{"text":"The authors report that Phonon topped the CPU streaming benchmark for time-to-first audio.","excerpt":"Speed is where we see Phonon truly shine, as the models top the CPU streaming benchmark on time-to-first audio.","support":"source-stated"},{"text":"The authors say Phonon 31m uses Apache 2.0, while the other models use CC BY-NC licenses.","excerpt":"Phonon 31m is Apache 2.0, so you can use it for free, even in a commercial product. The other models are CC BY-NC","support":"source-stated"},{"text":"The authors report more than 200,000 downloads in the first two weeks after launch.","excerpt":"Phonon was downloaded more than 200,000 times in its first two weeks","support":"source-stated"}],"limitations":["The article is written by the model’s creators and presents their account of its features, adoption and leaderboard performance.","Escape Meridian interpretation: the article’s reported leaderboard rankings do not establish performance across all devices or real-world uses.","The article describes demonstrations and leaderboard results but does not report comparative measurements of performance across the listed device types."],"mediaId":"c65c7708e93995ca45416c5ef4b52b70460b293ce45783d81126b519537db1b3","correctionReason":null,"id":"e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17","publicationId":"9b396f73-6184-4643-88f6-c1d75e843275","version":1,"sourceUrl":"https://huggingface.co/blog/phonon-tts","sourceTitle":"A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.","publisher":"Hugging Face","publishedAt":"2026-11-05T00:00:00.765Z","originalPublished":{"value":"2026-11-05T00:00:00.765Z","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-05T10:39:30.313Z","createdAt":"2026-11-10T04:17:42.024Z","historical":true,"entityIds":["hugging-face"],"topicIds":["intelligence-and-discovery","work-and-agency"],"media":[{"id":"c65c7708e93995ca45416c5ef4b52b70460b293ce45783d81126b519537db1b3","kind":"article","url":"https://huggingface.co/blog/phonon-tts","sourceUrl":"https://huggingface.co/blog/phonon-tts","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T04:09:36.082Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"found","sourceUrl":"https://huggingface.co/blog/phonon-tts","checkedAt":"2026-11-10T04:48:07.073Z","items":[],"note":"Media was declared by the source, but no asset passed the supported availability checks. Open the original source to view it."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"c65c7708e93995ca45416c5ef4b52b70460b293ce45783d81126b519537db1b3","confidence":0.99,"provider":"typesafe","model":"jev-1.13.0","inputHash":"0da18f36c9ef4dcad7a3b8adbd236dee159c4b12f538d6eb8de1b0bb4cd5fa6d","decidedAt":"2026-11-10T04:09:37.035Z"},"provenance":{"textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observationId":"fb8dcbcf44ac6c65eaac8bae1af3018d8821f427329cd08b393bc162850e10f8","retrievedAt":"2026-11-10T04:09:35.914Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"6f0f4683-dba2-427a-8ec6-51e83c102627"},"reviewer":{"model":"gpt-6-luna","runId":"5e0b82df-ed9e-4f80-8b00-8d9f815b815c"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T04:17:42.024Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Olesia Krizhevich","url":null,"kind":"Person"},{"name":"Laurent Mazare","url":null,"kind":"Person"},{"name":"Eric Bezzam","url":"https://huggingface.co/bezzam","kind":"Person"},{"name":"Eustache Le Bihan","url":"https://huggingface.co/eustlb","kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Olesia Krizhevich","url":null,"kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Olesia Krizhevich","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Laurent Mazare","url":null,"kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Laurent Mazare","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Eric Bezzam","url":"https://huggingface.co/bezzam","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Eric Bezzam","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Eustache Le Bihan","url":"https://huggingface.co/eustlb","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Eustache Le Bihan","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Hugging Face","url":"https://huggingface.co/","kind":"unknown","actorId":null},"role":"publisher","scope":{"kind":"publication","locator":null},"literalCredit":"Hugging Face","status":"stated","provenance":{"basis":"article-publisher","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.publisher"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":{"name":"Hugging Face","url":"https://huggingface.co/"},"sourceUrl":"https://huggingface.co/blog/phonon-tts","snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z","basis":"publisher-page-metadata","sourceLinks":69,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17/source"}},"canonicalUrl":"https://escapemeridian.com/readings/phonon-tts-the-authors-case-for-speech-generation-on-your-own-e6847a4c","formats":{"html":"/readings/phonon-tts-the-authors-case-for-speech-generation-on-your-own-e6847a4c","markdown":"/readings/phonon-tts-the-authors-case-for-speech-generation-on-your-own-e6847a4c.md","json":"/readings/phonon-tts-the-authors-case-for-speech-generation-on-your-own-e6847a4c.json"},"attribution":"Headline and summary by Escape Meridian, prepared by Luna from the attributed source. A source check is not independent confirmation of the source’s claims.","maintainedGuideLinks":[],"readerContext":{"version":"reader-context-v1","attribution":"Reference context selected by Escape Meridian; separate from source evidence. Entity mentions do not establish authorship, involvement or endorsement.","terms":[{"id":"term-cpu","name":"CPU","explanation":"The central processing unit: a general-purpose processor that carries out a computer's instructions.","referenceUrl":"https://aws.amazon.com/what-is/cpu/"},{"id":"term-benchmark","name":"Benchmark","explanation":"A defined set of tests used to compare systems. Results depend on the tasks and measures selected.","referenceUrl":"https://arxiv.org/abs/2211.09110"}],"entities":[{"id":"hugging-face","name":"Hugging Face","kind":"organization","context":"Hugging Face hosts models, datasets and software that let people share, adapt and inspect AI systems.","referenceUrls":["https://huggingface.co/blog"],"path":"/entities/hugging-face","json":"/entities/hugging-face.json","markdown":"/entities/hugging-face.md"},{"id":"time","name":"TIME","kind":"organization","context":"TIME is a news magazine publishing reporting on world affairs, business, technology and the workers behind digital services.","referenceUrls":["https://time.com/"],"path":"/entities/time","json":"/entities/time.json","markdown":"/entities/time.md"}]},"researchQuestions":[],"withdrawn":false,"references":{"schemaVersion":1,"target":{"type":"reading","id":"e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17","revision":"9b396f73-6184-4643-88f6-c1d75e843275","revisionKind":"publication-id","title":"Phonon TTS: the authors’ case for speech generation on your own device","url":"https://escapemeridian.com/readings/phonon-tts-the-authors-case-for-speech-generation-on-your-own-e6847a4c"},"source":{"type":"source","id":"https://huggingface.co/blog/phonon-tts","revision":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","revisionKind":"sha256-source-text","title":"A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.","url":"https://huggingface.co/blog/phonon-tts"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."},"revisions":[{"id":"e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17","title":"Phonon TTS: the authors’ case for speech generation on your own device","argument":"Phonon’s authors—Olesia Krizhevich, Laurent Mazare, Eric Bezzam and Eustache Le Bihan—describe a small text-to-speech model designed to run on a user’s device without a server or network. They argue that this keeps typed text on the device while making speech generation available offline. The authors say the release includes models of about 65 MB and 75 MB, covering English, French, German, Spanish and Portuguese, with more than 100 built-in voices. Licensing differs: Phonon 31m is Apache 2.0, while the other models are CC BY-NC. The authors report that Phonon ranks first for intelligibility in German and Spanish and in the top three in every language they evaluated; they also say it tops the CPU streaming benchmark for time-to-first audio. The article also describes demonstrations on devices including an Apple Watch and iPhone, and says Phonon was downloaded more than 200,000 times in its first two weeks. The authors present offline operation, small models and adaptable voices as the release’s central features, while noting that additional languages and custom models can be developed with design partners.","topicIds":["intelligence-and-discovery","work-and-agency"],"domain":"work","claimType":"attributed reading","limits":"The article is written by the model’s creators and presents their account of its features, adoption and leaderboard performance. Escape Meridian interpretation: the article’s reported leaderboard rankings do not establish performance across all devices or real-world uses. The article describes demonstrations and leaderboard results but does not report comparative measurements of performance across the listed device types.","speaker":{"name":"Olesia Krizhevich, Laurent Mazare, Eric Bezzam, Eustache Le Bihan","roleAtSource":"Article author"},"source":{"title":"A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.","publisher":"Hugging Face","format":"Article","url":"https://huggingface.co/blog/phonon-tts","publishedAt":"2026-11-05T00:00:00.765Z","dateBasis":"Date stated by the publisher."},"evidence":[{"text":"The authors describe Phonon as a text-to-speech model that runs on a user’s device without a server or network.","excerpt":"our small text-to-speech model that runs on your own device. It needs no server and no network","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors say the two models are about 65 MB and 75 MB and together cover five named languages.","excerpt":"Phonon comes in two sizes, at about 65 MB and 75 MB. Together they speak English, French, German, Spanish and Portuguese.","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors report first-place intelligibility rankings in German and Spanish, and top-three rankings in every language evaluated.","excerpt":"On intelligibility, Phonon ranks first in German and Spanish, and in the top three in every language we evaluated","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors report that Phonon topped the CPU streaming benchmark for time-to-first audio.","excerpt":"Speed is where we see Phonon truly shine, as the models top the CPU streaming benchmark on time-to-first audio.","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors say Phonon 31m uses Apache 2.0, while the other models use CC BY-NC licenses.","excerpt":"Phonon 31m is Apache 2.0, so you can use it for free, even in a commercial product. The other models are CC BY-NC","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"},{"text":"The authors report more than 200,000 downloads in the first two weeks after launch.","excerpt":"Phonon was downloaded more than 200,000 times in its first two weeks","url":"https://huggingface.co/blog/phonon-tts","relationship":"Source-stated"}],"sourceMedia":{"status":"found","sourceUrl":"https://huggingface.co/blog/phonon-tts","checkedAt":"2026-11-10T04:48:07.073Z","items":[],"note":"Media was declared by the source, but no asset passed the supported availability checks. Open the original source to view it."},"assumptions":[],"openQuestion":{"attribution":"Open question","text":"How do Phonon’s speed and intelligibility results vary across the different devices on which the authors say it runs?"},"whatWouldChangeView":{"attribution":"Change condition not recorded","text":""},"editorialComparisons":[],"live":{"title":"Phonon TTS: the authors’ case for speech generation on your own device","summary":"Phonon’s authors—Olesia Krizhevich, Laurent Mazare, Eric Bezzam and Eustache Le Bihan—describe a small text-to-speech model designed to run on a user’s device without a server or network. They argue that this keeps typed text on the device while making speech generation available offline. The authors say the release includes models of about 65 MB and 75 MB, covering English, French, German, Spanish and Portuguese, with more than 100 built-in voices. Licensing differs: Phonon 31m is Apache 2.0, while the other models are CC BY-NC. The authors report that Phonon ranks first for intelligibility in German and Spanish and in the top three in every language they evaluated; they also say it tops the CPU streaming benchmark for time-to-first audio. The article also describes demonstrations on devices including an Apple Watch and iPhone, and says Phonon was downloaded more than 200,000 times in its first two weeks. The authors present offline operation, small models and adaptable voices as the release’s central features, while noting that additional languages and custom models can be developed with design partners.","question":"How do Phonon’s speed and intelligibility results vary across the different devices on which the authors say it runs?","claims":[{"text":"The authors describe Phonon as a text-to-speech model that runs on a user’s device without a server or network.","excerpt":"our small text-to-speech model that runs on your own device. It needs no server and no network","support":"source-stated"},{"text":"The authors say the two models are about 65 MB and 75 MB and together cover five named languages.","excerpt":"Phonon comes in two sizes, at about 65 MB and 75 MB. Together they speak English, French, German, Spanish and Portuguese.","support":"source-stated"},{"text":"The authors report first-place intelligibility rankings in German and Spanish, and top-three rankings in every language evaluated.","excerpt":"On intelligibility, Phonon ranks first in German and Spanish, and in the top three in every language we evaluated","support":"source-stated"},{"text":"The authors report that Phonon topped the CPU streaming benchmark for time-to-first audio.","excerpt":"Speed is where we see Phonon truly shine, as the models top the CPU streaming benchmark on time-to-first audio.","support":"source-stated"},{"text":"The authors say Phonon 31m uses Apache 2.0, while the other models use CC BY-NC licenses.","excerpt":"Phonon 31m is Apache 2.0, so you can use it for free, even in a commercial product. The other models are CC BY-NC","support":"source-stated"},{"text":"The authors report more than 200,000 downloads in the first two weeks after launch.","excerpt":"Phonon was downloaded more than 200,000 times in its first two weeks","support":"source-stated"}],"limitations":["The article is written by the model’s creators and presents their account of its features, adoption and leaderboard performance.","Escape Meridian interpretation: the article’s reported leaderboard rankings do not establish performance across all devices or real-world uses.","The article describes demonstrations and leaderboard results but does not report comparative measurements of performance across the listed device types."],"mediaId":"c65c7708e93995ca45416c5ef4b52b70460b293ce45783d81126b519537db1b3","correctionReason":null,"id":"e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17","publicationId":"9b396f73-6184-4643-88f6-c1d75e843275","version":1,"sourceUrl":"https://huggingface.co/blog/phonon-tts","sourceTitle":"A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.","publisher":"Hugging Face","publishedAt":"2026-11-05T00:00:00.765Z","originalPublished":{"value":"2026-11-05T00:00:00.765Z","precision":"instant","basis":"publisher_page"},"firstObservedAt":"2026-11-05T10:39:30.313Z","createdAt":"2026-11-10T04:17:42.024Z","historical":true,"entityIds":["hugging-face"],"topicIds":["intelligence-and-discovery","work-and-agency"],"media":[{"id":"c65c7708e93995ca45416c5ef4b52b70460b293ce45783d81126b519537db1b3","kind":"article","url":"https://huggingface.co/blog/phonon-tts","sourceUrl":"https://huggingface.co/blog/phonon-tts","label":"Read original","provenance":"source_link","verification":{"status":"verified","checkedAt":"2026-11-10T04:09:36.082Z","method":"acquired_source","contentType":"text/html"},"recommendationReason":"Recommended by Jev for understanding this source; checked by Luna."}],"sourceMedia":{"status":"found","sourceUrl":"https://huggingface.co/blog/phonon-tts","checkedAt":"2026-11-10T04:48:07.073Z","items":[],"note":"Media was declared by the source, but no asset passed the supported availability checks. Open the original source to view it."},"editorialDecision":{"outcome":"accept","reasonCodes":["material_development"],"rubricVersion":"stream-admission-v5","mediaId":"c65c7708e93995ca45416c5ef4b52b70460b293ce45783d81126b519537db1b3","confidence":0.99,"provider":"typesafe","model":"jev-1.13.0","inputHash":"0da18f36c9ef4dcad7a3b8adbd236dee159c4b12f538d6eb8de1b0bb4cd5fa6d","decidedAt":"2026-11-10T04:09:37.035Z"},"provenance":{"textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observationId":"fb8dcbcf44ac6c65eaac8bae1af3018d8821f427329cd08b393bc162850e10f8","retrievedAt":"2026-11-10T04:09:35.914Z","kind":"publisher-page","preparer":{"model":"gpt-6-luna","runId":"6f0f4683-dba2-427a-8ec6-51e83c102627"},"reviewer":{"model":"gpt-6-luna","runId":"5e0b82df-ed9e-4f80-8b00-8d9f815b815c"}},"audit":{"status":"uncertain","reviewedAt":"2026-11-10T04:17:42.024Z","model":"anthropic/claude-opus-5.5"},"sourceAttribution":{"authors":[{"name":"Olesia Krizhevich","url":null,"kind":"Person"},{"name":"Laurent Mazare","url":null,"kind":"Person"},{"name":"Eric Bezzam","url":"https://huggingface.co/bezzam","kind":"Person"},{"name":"Eustache Le Bihan","url":"https://huggingface.co/eustlb","kind":"Person"}],"authorRole":"article-author","hosts":[],"status":"stated","authorRoster":{"truncated":false,"omitted":0,"assertionGroupsOmitted":0},"participation":[{"actor":{"name":"Olesia Krizhevich","url":null,"kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Olesia Krizhevich","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:0","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Laurent Mazare","url":null,"kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Laurent Mazare","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:1","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Eric Bezzam","url":"https://huggingface.co/bezzam","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Eric Bezzam","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:2","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Eustache Le Bihan","url":"https://huggingface.co/eustlb","kind":"Person","actorId":null},"role":"author","scope":{"kind":"work-credit","locator":null},"literalCredit":"Eustache Le Bihan","status":"stated","provenance":{"basis":"article-jsonld","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.author"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:3","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}},{"actor":{"name":"Hugging Face","url":"https://huggingface.co/","kind":"unknown","actorId":null},"role":"publisher","scope":{"kind":"publication","locator":null},"literalCredit":"Hugging Face","status":"stated","provenance":{"basis":"article-publisher","sourceUrl":"https://huggingface.co/blog/phonon-tts","locator":"document/html[1]/head[0]/script[41]@2242.publisher"},"assertionId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0:participation:4","identity":{"version":"entity-identity-v1","status":"unresolved","actorId":null,"canonicalActorId":null,"candidateActorIds":[],"assertions":[],"sourceObservedAt":"2026-11-10T04:24:09.971Z","knowledgeAsOf":null},"sourceVersion":{"snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","sourceUrl":"https://huggingface.co/blog/phonon-tts","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z"}}],"participationCoverage":{"total":5,"returned":5,"complete":true,"fullAssertions":"source-metadata-endpoint"},"distribution":null,"publisher":{"name":"Hugging Face","url":"https://huggingface.co/"},"sourceUrl":"https://huggingface.co/blog/phonon-tts","snapshotId":"360a3cabbe94a450094f35c47507b461c7dbc5a9f80f630b37bc547394ca28e0","contentSha256":"5adb8b218eb96dbb04544573af1391515745356a7824c4e9c993e0f619d0bb1d","textHash":"913dade1c0ee7ff16949414ed1c2cfaa39e3b713048a9cf208f8731a99bf3727","observedAt":"2026-11-10T04:24:09.971Z","basis":"publisher-page-metadata","sourceLinks":69,"linksTruncated":false,"metadataUrl":"/api/pipeline/stream/e6847a4c17be90aefdce5424db493a9f9f374bf8c50c69dc2dd9c4f8e4671c17/source"}}}],"audits":[{"publicationId":"9b396f73-6184-4643-88f6-c1d75e843275","verdict":"uncertain","findings":[{"dimension":"attribution","status":"pass","explanation":"The reading correctly attributes the post to its four named authors from the Phonon/Gradium team and keeps performance, adoption and feature claims as their assertions. A limitation also notes that the creators are describing their own model. The reader comment is not misattributed.","excerpt":"Two weeks ago, we opened up Phonon, our small text-to-speech model that runs on your own device."},{"dimension":"summary","status":"uncertain","explanation":"The summary is faithful but leaves central context unclear for general readers. (1) It says the licensing differs but does not explain the distinction the source draws: Apache 2.0 allows free commercial use, while CC BY-NC is for non-commercial use only. Smallest repair: add a clause stating this. (2) It reports rankings without naming the source ranking, Hugging Face's Open TTS Leaderboard. It also omits that intelligibility there means word error rate and that time-to-first audio measures how quickly speech starts. (3) It drops the authors' context that rivals were models up to 100 times larger.","excerpt":"Phonon 31m is Apache 2.0, so you can use it for free, even in a commercial product. The other models are CC BY-NC, so they’re free for non-commercial projects."},{"dimension":"date","status":"pass","explanation":"originalPublished (2026-11-05) matches the page's stated publication date. The earlier April announcement and the model release two weeks before the post are events described in the text, not the publication date of this source.","excerpt":"Published\nNovember 5, 2026"},{"dimension":"support","status":"pass","explanation":"Every claim matches an exact source excerpt and remains attributed. The Escape Meridian interpretation is labeled. The question about device-level variation follows from the source's list of supported devices and the absence of per-device measurements. The reading invents no benefits, costs or forecasts.","excerpt":"On intelligibility, Phonon ranks first in German and Spanish, and in the top three in every language we evaluated, next to models up to 100 times its size."},{"dimension":"media","status":"pass","explanation":"The selected media is the verified direct link to the original Hugging Face blog post, which is the most direct way to access the source.","excerpt":null}],"createdAt":"2026-11-10T04:17:42.024Z","model":"anthropic/claude-opus-5.5"}],"correctionUrl":"https://escapemeridian.com/corrections/"}