Hackernews posts about TTS

1. 01
   

   newShow HN: Nari Qwen3-TTS and Qwen3-ASR – High accuracy, low latency and costnarilabs.com

   ▲ 92toebee20d💬 31savesaved
2. 02
   

   newThe STT-LLM-TTS voice stack is deadwww.skeptrune.com

   ▲ 6skeptrune2d💬 1savesaved
3. 03
   

   newShow HN: Ito – streaming neural TTS for the ESP32-S3 (4.9 MB, no NPU, no cloud)github.com

   ▲ 2dani-lokutor2d💬 2savesaved
4. 04
   

   newShow HN: Fusion-runtime – self-hosted voice agents, STT+LLM+TTS in one processgithub.com

   ▲ 2samarthurs1813d💬 1savesaved
5. 05
   

   newGemini vs. Elevenlabs: TTS and Voice Cloningtechstackups.com

   ▲ 2ritzaco2ddiscusssavesaved
6. 06
   

   newShow HN: Airy TTS – 2K characters/second, $2 per 1M charactersairy.so

   ▲ 2login58817ddiscusssavesaved
7. 07
   

   newShow HN: Loudkit, Local TTS with Native Swift, Go, Rust and TypeScript Portsgithub.com

   ▲ 2mowmiatlas24ddiscusssavesaved
8. 08
   

   newTrain your own custom Tiny TTS model from scratch overnight on consumer hardwaregithub.com

   ▲ 2FranciscoCarlos27ddiscusssavesaved
9. 09
   

   newSpeech2Speech – browser-based STT and TTS for interacting with local LLMsgithub.com

   ▲ 2Curiositry28ddiscusssavesaved
10. 10
    

    newShow HN: Kokoro TTS in the browser, 41 voices in 6 languages, runs locallysandbook.app

    ▲ 1mazzystar36h💬 1savesaved
11. 11
    

    newShow HN: 10x cheaper TTS at 50ms time-to-first-audionarilabs.com

    ▲ 1toebee24d💬 1savesaved
12. 12
    

    newShow HN: Portable Kokoro TTS binary with g2p, normalizer, lexicon, and guessergithub.com

    ▲ 1robviren2ddiscusssavesaved
13. 13
    

    newShow HN: Greek and Cypriot Greek TTS that runs faster than real time on CPUhuggingface.co

    ▲ 1antonios_makro5ddiscusssavesaved
14. 14
    

    newShow HN: Voice cloning for a TTS whose style encoder was never releasedgithub.com

    ▲ 1kdrkdrkdr9ddiscusssavesaved
15. 15
    

    newGemini 3.8 TTS Playgroundsimonwillison.net

    ▲ 1lumpa11ddiscusssavesaved
16. 16
    

    newQwen-Audio-3.1-TTSfun-resource-shanghai.oss-cn-shanghai.aliyuncs.com

    ▲ 1nthypes11ddiscusssavesaved
17. 17
    

    newShow HN: Open-source simulation testing infra for voice agentsgithub.com

    ▲ 16Nischalj1024d💬 7savesaved
18. 18
    

    newShow HN: Jinfer – AI inference engine for the JVM. AI in a jarqxotic.ai

    ▲ 6mukel19d💬 1savesaved
19. 19
    

    newShow HN: Chronicle – Local-first, open-source authoring software for writerspazvanti.github.io

    ▲ 3pazvanti19d💬 10savesaved
20. 20
    

    newAsk HN: Replicate ChatGPT/Anthropic Voice Mode?

    ▲ 3tito29ddiscusssavesaved
21. 21
    

    newAsk HN: Best sentence corpora with native audio for language learning?

    ▲ 1treetalker27d💬 2savesaved
22. 22
    

    newAsk HN: Why are Gemini Flash 3.8 LIVE Voices sooo limited?

    ▲ 1artur_makly6ddiscusssavesaved
23. 23
    

    newShow HN: Giving my inner monologue autocomplete, with my own voicewww.maximevidal.com

    ▲ 1vmaxmc29ddiscusssavesaved
24. 24
    

    newBuilding Jarvis: a better voice starts before trainingfpl.dev

    ▲ 1ajmwagar25d💬 1savesaved
25. 25
    

    newI'm being cyberattacked by Tesla, Incdreamstation.systems

    ▲ 458robinpie21d💬 119savesaved
26. 26
    

    newNorth Korean nuclear test sets off years of earthquakeswww.science.org

    ▲ 225rbanffy16d💬 181savesaved
27. 27
    

    newApple iPhone 18 Pro Camera testwww.dxomark.com

    ▲ 208luu15d💬 182savesaved
28. 28
    

    newPlunging test scores are a slow-moving catastrophewww.economist.com

    ▲ 207vinni28d💬 413savesaved
29. 29
    

    newHow well do agents use test/verification techniques?danluu.com

    ▲ 191vinhnx27d💬 71savesaved
30. 30
    

    newClassified estimates show the NSA is paying billions to test AI modelswww.washingtonsun.com

    ▲ 178rdmuser9d💬 108savesaved

· edit