--- title: "Why TTS Models Now Look Like LLMs — Samuel Humeau, Mistral" url: https://daily.dev/posts/why-tts-models-now-look-like-llms-samuel-humeau-mistral-fkow9i3dv source_url: https://www.youtube.com/watch?v=3jGAU2sbAyY type: video:youtube source: "AI Engineer" published: 2026-05-09T17:26:53.190Z updated: 2026-05-09T17:27:14.575Z tags: ["llm", "text-to-speech", "mistral-ai", "voice-cloning"] reading_time: 22 upvotes: 2 comments: 0 language: 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. # Why TTS Models Now Look Like LLMs — Samuel Humeau, Mistral **[AI Engineer](https://daily.dev/sources/aidotengineer)** · 22 min read · 2 upvotes · 0 comments ## Summary A Mistral AI scientist presents the architecture behind modern text-to-speech (TTS) models, explaining why they increasingly resemble LLMs. Key topics include: framing TTS as a language modeling problem using autoregressive decoders, audio tokenization via codecs (compressing audio frames into discrete tokens), the challenge of high audio bitrates vs. sparse text information, and latency reduction through streaming audio packets. The talk also covers Mistral's newly released open-source TTS model, which uses a diffusion/flow-matching approach for token generation per frame, voice cloning capabilities (with the encoder kept proprietary), and architectural patterns for real-time text-input streaming in voice agent pipelines. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [A Guide to Voice Cloning on Voxtral with a Missing Encoder](https://daily.dev/posts/a-guide-to-voice-cloning-on-voxtral-with-a-missing-encoder-9kkzy5kpb) · Towards Data Science · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#text-to-speech](https://daily.dev/tags/text-to-speech), [#mistral-ai](https://daily.dev/tags/mistral-ai), [#voice-cloning](https://daily.dev/tags/voice-cloning) [View this post on daily.dev](https://daily.dev/posts/why-tts-models-now-look-like-llms-samuel-humeau-mistral-fkow9i3dv)