--- title: WhisperSpeech makes its way to AI.dev | daily.dev description: Collabora is presenting WhisperSpeech, their open source text-to-speech model, at the inaugural AI.dev: Open Source GenAI & ML Summit in San Jose. The talk by... canonical: https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: WhisperSpeech makes its way to AI.dev | daily.dev og:description: Collabora is presenting WhisperSpeech, their open source text-to-speech model, at the inaugural AI.dev: Open Source GenAI & ML Summit in San Jose. The talk by... og:url: https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx og:image: https://api.daily.dev/og/posts/lT2lgM5ZX.png og:image:alt: WhisperSpeech makes its way to AI.dev og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # WhisperSpeech makes its way to AI.dev **[Collabora Blog](https://daily.dev/sources/collabora)** · 2 min read · 0 upvotes · 0 comments ## Summary Collabora is presenting WhisperSpeech, their open source text-to-speech model, at the inaugural AI.dev: Open Source GenAI & ML Summit in San Jose. The talk by Jakub Piotr Cłapa covers how Collabora scaled its models and training pipelines from hundreds to 80,000+ hours of speech recordings, lessons learned, and challenges encountered. WhisperSpeech is built on properly licensed speech datasets and unrestricted open source code, aiming to deliver natural-sounding speech synthesis. A video recording of the talk is available. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How did Collabora scale WhisperSpeech training data from hundreds to 80,000+ hours of speech? WhisperSpeech was scaled from hundreds to 80,000+ hours of speech recordings by Collabora, with lessons and challenges shared by Jakub Piotr Cłapa at AI.dev. The model is built entirely on properly licensed speech datasets and unrestricted open source code, targeting natural-sounding speech synthesis. Specific pipeline tricks were detailed in the conference talk, with a video recording available. _Developers working on open source speech synthesis track scaling approaches and dataset strategies on daily.dev._ ## Similar posts on daily.dev - [From local prototype to enterprise production: Private speech transcription with Whisper and Red Hat AI](https://daily.dev/posts/from-local-prototype-to-enterprise-production-private-speech-transcription-with-whisper-and-red-hat-hqggegkqh) · Red Hat Developer · 0 upvotes · 0 comments - [Real-Time translated speech pipeline with Whisper and Soprano](https://daily.dev/posts/real-time-translated-speech-pipeline-with-whisper-and-soprano-wqus4v8ef) · DigitalOcean Community · 0 upvotes · 0 comments - [Whisper transcribed a two-hour meeting on my laptop in four minutes, and none of it left the room](https://daily.dev/posts/whisper-transcribed-a-two-hour-meeting-on-my-laptop-in-four-minutes-and-none-of-it-left-the-room-jxk0grpcc) · XDA Developers · 1 upvotes · 0 comments - [Type with your voice on Linux using this Whisper-based app](https://daily.dev/posts/type-with-your-voice-on-linux-using-this-whisper-based-app-jsd1jlcfz) · omg\! ubuntu\! · 0 upvotes · 0 comments --- Tags: [#machine-learning](https://daily.dev/tags/machine-learning), [#deep-learning](https://daily.dev/tags/deep-learning), [#text-to-speech](https://daily.dev/tags/text-to-speech) [View this post on daily.dev](https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"WhisperSpeech makes its way to AI.dev","url":"https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx"},"datePublished":"2026-08-11T08:56:14.983Z","dateModified":"2026-08-11T09:24:26.897Z","description":"Collabora is presenting WhisperSpeech, their open source text-to-speech model, at the inaugural AI.dev: Open Source GenAI & ML Summit in San Jose. The talk by...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3575eb5a2150e833640f0915b8f0d6b0?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/3575eb5a2150e833640f0915b8f0d6b0?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collabora Blog","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collabora Blog","logo":"https://media.daily.dev/image/upload/s--ZGZ0FjqS--/f_auto,q_auto/v1786438306/logos/collabora?_a=BAMAMicg0","url":"https://daily.dev/sources/collabora"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"machine-learning,deep-learning,text-to-speech","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collabora Blog","item":"https://daily.dev/sources/collabora"},{"@type":"ListItem","position":3,"name":"WhisperSpeech makes its way to AI.dev"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/whisperspeech-makes-its-way-to-ai-dev-lt2lgm5zx#faq","mainEntity":[{"@type":"Question","name":"How did Collabora scale WhisperSpeech training data from hundreds to 80,000+ hours of speech?","acceptedAnswer":{"@type":"Answer","text":"WhisperSpeech was scaled from hundreds to 80,000+ hours of speech recordings by Collabora, with lessons and challenges shared by Jakub Piotr Cłapa at AI.dev. The model is built entirely on properly licensed speech datasets and unrestricted open source code, targeting natural-sounding speech synthesis. Specific pipeline tricks were detailed in the conference talk, with a video recording available. Developers working on open source speech synthesis track scaling approaches and dataset strategies on daily.dev."}}]} ```