AI article
Four on-device TTS models on one CPU core: LinnetTTS, Piper, Kokoro, pocket-tts
Community description: Most CPU TTS writeups benchmark one model in isolation. When you are building a voice product, that...
Dev.to | Nov 6, 2026 | VoxRT
Automated excerpt
Most CPU TTS writeups benchmark one model in isolation. Four open-source TTS models fit under 100 M parameters and target consumer CPUs: LinnetTTS 41 M (VoxRT), Piper medium 16 M (OHF-Voice, originally Rhasspy), Kokoro-82M (hexgrad), and pocket-tts 100 M (Kyutai Labs). Raw model-weight files on disk tell a different story: Piper 64 MB, Linnet 83 MB fp16, pocket-tts 236 MB, Kokoro 326 MB.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.