{"slug": "pocket-tts", "name": "Pocket-TTS", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 4, "commenters": 7, "warners": 0, "score": 3.744, "rising": 0.02, "first": "2026-01-23", "latest": "2026-10-21", "why": "which is just 100M params, and excellent in both speed and quality (English only). I use it in my voice plugin", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 3, "compare": 1, "warn": 0}, "spark": [0, 0, 2, 1, 0, 1, 0, 0, 1, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "which is just 100M params, and excellent in both speed and quality (English only). I use it in my voice plugin", "icon": true, "domain": null, "github_repo": "github.com/kyutai-labs/pocket-tts", "official_url": "https://github.com/kyutai-labs/pocket-tts", "pricing": "", "aliases": ["Pocket-TTS", "Pocket TTS", "PocketTTS", "pocket-tts", "pocket-TTS"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 790282625, "item_id": 49392664, "url": "https://news.ycombinator.com/item?id=49392664", "by": "armcat", "date": "2026-08-21", "stance": "recommend", "quote": "I've now been using Pocket TTS which is super fast", "excerpt": "Having built my own voice assistant (https://github.com/acatovic/ova) and having tried many other services and models, I feel the real win is when this is on-device, and by \"on-device\" I mean being very inexpensive to run on a phone, and not H100. I've now been using Pocket TTS which is super fast, and also Chatterbox and Fish Audio S2 Pro (on the Mac/PC), I feel we are so close, yet so far. The quality is amazing, b", "context": "", "use_case": "on-device text-to-speech", "switched_from": "", "story": "How We Made a Text-to-Speech Model Respond in Sub-50 ms"}, {"id": 781157265, "item_id": 48822329, "url": "https://news.ycombinator.com/item?id=48822329", "by": "teravor", "date": "2026-07-07", "stance": "recommend", "quote": "pocket-tts is much better especially when you rip a good voice", "excerpt": "kokoro is decent but pocket-tts is much better especially when you rip a good voice. https://github.com/kyutai-labs/pocket-tts the onnx version of pocket-tts does perform better. https://huggingface.co/KevinAHM/pocket-tts-onnx", "context": "", "use_case": "local text-to-speech", "switched_from": "", "story": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro"}, {"id": 767173634, "item_id": 47948352, "url": "https://news.ycombinator.com/item?id=47948352", "by": "d4rkp4ttern", "date": "2026-04-29", "stance": "recommend", "quote": "TTS using KyutAI\u2019s Pocket-TTS, an amazing 100M-param model.", "excerpt": "This was on HN 7 months ago: https://news.ycombinator.com/item?id=45114245 Every time a STT/TTS model is posted I wonder if it will change my current workflow on MacOS, which is: STT with Parakeet-V3 via Hex [1] app for near-instant good-enough transcription for talking to AI agents. TTS using KyutAI\u2019s Pocket-TTS, an amazing 100M-param model. I used this to make a \"voice\" plugin [2] for Claude Code So far I haven\u2019t s", "context": "macOS user", "use_case": "text-to-speech", "switched_from": "", "story": "Microsoft VibeVoice: Open-Source Frontier Voice AI"}, {"id": 752548578, "item_id": 47034286, "url": "https://news.ycombinator.com/item?id=47034286", "by": "d4rkp4ttern", "date": "2026-02-16", "stance": "recommend", "quote": "just 100M params, and amazing speech quality (English only)", "excerpt": "It's amazing how good open-weight STT and TTS have gotten, so there's no need to subs for Wispr Flow, Superwhisper, Eleven-Labs etc. Sharing my setup in case it may be useful for others; it's especially useful when working with CLI agents like Code Code or Codex-CLI: STT: Hex [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immate", "context": "", "use_case": "text-to-speech", "switched_from": "", "story": "Why Audio Is the One Area Small Labs Are Winning"}, {"id": 751821216, "item_id": 46988826, "url": "https://news.ycombinator.com/item?id=46988826", "by": "d4rkp4ttern", "date": "2026-02-12", "stance": "recommend", "quote": "I used the amazing 100M-parameter Pocket-TTS [1] model", "excerpt": "Related: I used the amazing 100M-parameter Pocket-TTS [1] model to make a stop-hook based voice plugin [2] that lets Claude Code give a short voice update whenever it stops. The hook quietly inserts nudges to Claude Code to end its response with a short speakable summary, and in case it forgets, it uses a headless agent to create the summary. It was trickier than I expected, to get it working well: FFMpeg pipe stream", "context": "", "use_case": "voice updates from Claude Code", "switched_from": "", "story": "Warcraft III Peon Voice Notifications for Claude Code"}]}], "caveats": [], "who": [{"by": "d4rkp4ttern", "context": "macOS user", "url": "https://news.ycombinator.com/item?id=47948352", "date": "2026-04-29"}], "tags": [], "use_cases": ["text-to-speech", "voice updates from claude code", "local text-to-speech", "text to speech", "tts in memoe app", "on-device text-to-speech"], "compared": [{"slug": "parakeet", "name": "Parakeet", "co": 5, "switched_from": 0, "switched_to": 0}, {"slug": "handy", "name": "Handy", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "hex", "name": "Hex", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "superwhisper", "name": "Superwhisper", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "elevenlabs", "name": "ElevenLabs", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46731068", "title": "Ask HN: What's the current best local/open speech-to-speech setup?", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=48911793", "title": "Speech Recognition and TTS in less than 500kb", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50181563", "title": "Gemini vs. ElevenLabs Voice Cloning and TTS", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49389952", "title": "How We Made a Text-to-Speech Model Respond in Sub-50 ms", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48821576", "title": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47933236", "title": "Microsoft VibeVoice: Open-Source Frontier Voice AI", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {"recommend": 2}, "2026-02": {"recommend": 1, "neutral": 1}, "2026-03": {}, "2026-04": {"recommend": 1}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 1, "neutral": 1, "compare": 1}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"neutral": 1}}, "quotes": [{"id": 802906673, "item_id": 50181667, "url": "https://news.ycombinator.com/item?id=50181667", "by": "yisraelgottz", "date": "2026-10-21", "stance": "neutral", "quote": "I use PocketTTS for Memoe", "excerpt": "Hey I think ElevenLabs clears. I use PocketTTS for Memoe (https://github.com/memoe-app/memoe)", "context": "", "use_case": "TTS in Memoe app", "switched_from": "", "story": "Gemini vs. ElevenLabs Voice Cloning and TTS"}, {"id": 790282625, "item_id": 49392664, "url": "https://news.ycombinator.com/item?id=49392664", "by": "armcat", "date": "2026-08-21", "stance": "recommend", "quote": "I've now been using Pocket TTS which is super fast", "excerpt": "Having built my own voice assistant (https://github.com/acatovic/ova) and having tried many other services and models, I feel the real win is when this is on-device, and by \"on-device\" I mean being very inexpensive to run on a phone, and not H100. I've now been using Pocket TTS which is super fast, and also Chatterbox and Fish Audio S2 Pro (on the Mac/PC), I feel we are so close, yet so far. The quality is amazing, b", "context": "", "use_case": "on-device text-to-speech", "switched_from": "", "story": "How We Made a Text-to-Speech Model Respond in Sub-50 ms"}, {"id": 783512496, "item_id": 48969531, "url": "https://news.ycombinator.com/item?id=48969531", "by": "yako21000", "date": "2026-07-19", "stance": "compare", "quote": "is there a comparison to https://github.com/kyutai-labs/pocket-tts ?", "excerpt": "wow now that's a really tiny tts model. is there a comparison to https://github.com/kyutai-labs/pocket-tts ?", "context": "", "use_case": "text-to-speech", "switched_from": "", "story": "Speech Recognition and TTS in less than 500kb"}, {"id": 783497235, "item_id": 48968577, "url": "https://news.ycombinator.com/item?id=48968577", "by": "d4rkp4ttern", "date": "2026-07-19", "stance": "neutral", "quote": "I found it fun to make a voice plugin for Claude Code that uses PocketTTS", "excerpt": "I use the Hex[1] app on MacOs for near instant transcription with Parakeet V3. This is how I speak to Code agents at least 80% of the time. The idea is - I tend to be lazy if I need to type lots of details, so speaking lets me get into details that I otherwise wouldn\u2019t and this helps give more useful context to the agent. This often tends to be an unstructured brain dump so I sometimes ask the agent to repeat back wh", "context": "", "use_case": "voice updates from Claude Code", "switched_from": "", "story": "Speech Recognition and TTS in less than 500kb"}, {"id": 781157265, "item_id": 48822329, "url": "https://news.ycombinator.com/item?id=48822329", "by": "teravor", "date": "2026-07-07", "stance": "recommend", "quote": "pocket-tts is much better especially when you rip a good voice", "excerpt": "kokoro is decent but pocket-tts is much better especially when you rip a good voice. https://github.com/kyutai-labs/pocket-tts the onnx version of pocket-tts does perform better. https://huggingface.co/KevinAHM/pocket-tts-onnx", "context": "", "use_case": "local text-to-speech", "switched_from": "", "story": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro"}, {"id": 767173634, "item_id": 47948352, "url": "https://news.ycombinator.com/item?id=47948352", "by": "d4rkp4ttern", "date": "2026-04-29", "stance": "recommend", "quote": "TTS using KyutAI\u2019s Pocket-TTS, an amazing 100M-param model.", "excerpt": "This was on HN 7 months ago: https://news.ycombinator.com/item?id=45114245 Every time a STT/TTS model is posted I wonder if it will change my current workflow on MacOS, which is: STT with Parakeet-V3 via Hex [1] app for near-instant good-enough transcription for talking to AI agents. TTS using KyutAI\u2019s Pocket-TTS, an amazing 100M-param model. I used this to make a \"voice\" plugin [2] for Claude Code So far I haven\u2019t s", "context": "macOS user", "use_case": "text-to-speech", "switched_from": "", "story": "Microsoft VibeVoice: Open-Source Frontier Voice AI"}, {"id": 753028373, "item_id": 47064273, "url": "https://news.ycombinator.com/item?id=47064273", "by": "Blair_Erickson", "date": "2026-02-18", "stance": "neutral", "quote": "PocketTTS running locally", "excerpt": "I'm Blair, one of the creators of PearlOS. Here's what we've built. PearlOS is a self-evolving operating system. You talk to her, she builds, creates, informs, learns, evolves. This is an open source browser-based, voice and touch desktop environment powered by an intelligent learning companion named Pearl. Pearl has full awareness and control of your visual and audio experience inside PearlOS in real time, so you ca", "context": "", "use_case": "local text-to-speech", "switched_from": "", "story": "Show HN: PearlOS \u2013An open source OS companion that learns and evolves around you"}, {"id": 752548578, "item_id": 47034286, "url": "https://news.ycombinator.com/item?id=47034286", "by": "d4rkp4ttern", "date": "2026-02-16", "stance": "recommend", "quote": "just 100M params, and amazing speech quality (English only)", "excerpt": "It's amazing how good open-weight STT and TTS have gotten, so there's no need to subs for Wispr Flow, Superwhisper, Eleven-Labs etc. Sharing my setup in case it may be useful for others; it's especially useful when working with CLI agents like Code Code or Codex-CLI: STT: Hex [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative to bigger models is immate", "context": "", "use_case": "text-to-speech", "switched_from": "", "story": "Why Audio Is the One Area Small Labs Are Winning"}, {"id": 751821216, "item_id": 46988826, "url": "https://news.ycombinator.com/item?id=46988826", "by": "d4rkp4ttern", "date": "2026-02-12", "stance": "recommend", "quote": "I used the amazing 100M-parameter Pocket-TTS [1] model", "excerpt": "Related: I used the amazing 100M-parameter Pocket-TTS [1] model to make a stop-hook based voice plugin [2] that lets Claude Code give a short voice update whenever it stops. The hook quietly inserts nudges to Claude Code to end its response with a short speakable summary, and in case it forgets, it uses a headless agent to create the summary. It was trickier than I expected, to get it working well: FFMpeg pipe stream", "context": "", "use_case": "voice updates from Claude Code", "switched_from": "", "story": "Warcraft III Peon Voice Notifications for Claude Code"}, {"id": 749279297, "item_id": 46829956, "url": "https://news.ycombinator.com/item?id=46829956", "by": "d4rkp4ttern", "date": "2026-01-30", "stance": "recommend", "quote": "there\u2019s really no advantage over pocket TTS.", "excerpt": "So I benchmarked it and there\u2019s really no advantage over pocket TTS. There are some tradeoffs like Kitten doesn\u2019t have streaming audio.", "context": "", "use_case": "text to speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 747890178, "item_id": 46743136, "url": "https://news.ycombinator.com/item?id=46743136", "by": "d4rkp4ttern", "date": "2026-01-24", "stance": "recommend", "quote": "just 100M params, and amazing speech quality (English only).", "excerpt": "This is not strictly speech-to-speech, but I quite like it when working with Claude Code or other CLI Agents: STT: Handy [1] (open-source), with Parakeet V3 - stunningly fast, near-instant transcription. The slight accuracy drop relative bigger models is immaterial when you're talking to an AI. I always ask it to restate back to me what it understood, and it gives back a nicely structured version -- this helps confir", "context": "", "use_case": "text to speech", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 747869427, "item_id": 46741839, "url": "https://news.ycombinator.com/item?id=46741839", "by": "andhuman", "date": "2026-01-23", "stance": "recommend", "quote": "Pocket is small and fast and has good enough voice cloning.", "excerpt": "I built this recently. I used nvidia parakeet as STT, open wake word as the wake word detection, mistral ministral 14b as LLM and pocket tts for tts. Fits snugly in my 16 gb VRAM. Pocket is small and fast and has good enough voice cloning. I first used the chatterbox turbo model, which perform better and even supported some simple paralinguistic word like (chuckle) that made it more fun, but it was just a bit too big", "context": "", "use_case": "text-to-speech", "switched_from": "Chatterbox Turbo", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 747706432, "item_id": 46731652, "url": "https://news.ycombinator.com/item?id=46731652", "by": "d4rkp4ttern", "date": "2026-01-23", "stance": "recommend", "quote": "which is just 100M params, and excellent in both speed and quality (English only). I use it in my voice plugin", "excerpt": "Curious how it compares to last week\u2019s release of Kyutai\u2019s Pocket-TTS [1] which is just 100M params, and excellent in both speed and quality (English only). I use it in my voice plugin [2] for quick voice updates in Claude Code. [1] https://github.com/kyutai-labs/pocket-tts [2] https://github.com/pchalasani/claude-code-tools?tab=readme-ov-file#-voice-plugin", "context": "", "use_case": "text-to-speech for Claude Code", "switched_from": "", "story": "Qwen3-TTS Family Is Now Open Sourced: Voice Design, Clone, and Generation"}]}