# Qwen3-TTS 41 Hacker News commenters recommended Qwen3-TTS and 13 criticized it, November 2025 to November 2026. It was recommended in 7 of 13 months. It meets the Hacker Approved badge rule. **Verdict:** Open-source text-to-speech model that clones voices well and runs locally, though it needs a GPU for real-time use and can be inconsistent across clips. ## Why people recommend it - Strong voice cloning quality (5 comments): "The real value I see is being able to clone a voice and change timbre and characteristics of the voice" ([source](https://news.ycombinator.com/item?id=46721801)) "It definitely kind of sounds like me, but I like it much better than listening to my real voice." ([source](https://news.ycombinator.com/item?id=46728392)) "It has great voice cloning capabilities and creates rich speech with emotions with low latency." ([source](https://news.ycombinator.com/item?id=46731119)) - Natural, expressive speech (6 comments): "It has great voice cloning capabilities and creates rich speech with emotions with low latency." ([source](https://news.ycombinator.com/item?id=46731119)) "it was mind blowingly good, you can even provide directions for the overall tone etc." ([source](https://news.ycombinator.com/item?id=46878014)) "Some of the demos arguably sounded way better than a lot of indie voice-acting." ([source](https://news.ycombinator.com/item?id=46726305)) - Runs locally on own hardware (4 comments): "There are some samples. If you have GPU you might want to fork and improve this, but otherwise slow, but usable on CPU as well." ([source](https://news.ycombinator.com/item?id=46724459)) "I got this running on macOS using mlx-audio thanks to Prince Canuma" ([source](https://news.ycombinator.com/item?id=46726440)) "It runs locally and I can run it as many times as I want." ([source](https://news.ycombinator.com/item?id=48825291)) - Low latency and low cost (2 comments): "It has great voice cloning capabilities and creates rich speech with emotions with low latency." ([source](https://news.ycombinator.com/item?id=46731119)) "dirt cheap at $5 per 1M characters, still faster than industry avg at 200 ms TTFA" ([source](https://news.ycombinator.com/item?id=49646415)) ## What people warn about - Slow on CPU, needs GPU (4 comments): "Demo ran fine, if very slowly, with CPU-only" ([source](https://news.ycombinator.com/item?id=46731519)) "The current code doesn't appear very optimized. Running on CPU-only it only uses four threads for example" ([source](https://news.ycombinator.com/item?id=46732006)) "qwen 3 tts was also great but its unisable as any real time agentic voice as its too slow" ([source](https://news.ycombinator.com/item?id=46748163)) - Inconsistent quality between clips (2 comments): "Unfortunately each snippet varies drastically in quality" ([source](https://news.ycombinator.com/item?id=46723117)) "it switched voices half way through a 33 second clip" ([source](https://news.ycombinator.com/item?id=49701701)) - Wrong pronunciation or accent (3 comments): "one of their examples (the final Age Control example) is prompted to have American English as an accent, but sounds like an Australian" ([source](https://news.ycombinator.com/item?id=46725611)) "Qwen only has one pitch accent for pure hiragana words" ([source](https://news.ycombinator.com/item?id=47449636)) "one of it pronounces taskete as itsukete" ([source](https://news.ycombinator.com/item?id=46727546)) - Some voices sound childish or anime-like (2 comments): "The normal speech voices are fine (lower than the anime ones on the page.) i agree that the first few are very infantile." ([source](https://news.ycombinator.com/item?id=46724122)) "do most of the english audio samples sound like anime voices?" ([source](https://news.ycombinator.com/item?id=46720540)) ## Alternatives hackers recommend - [ElevenLabs](https://hackerapproved.com/p/elevenlabs.md): 59 recommend - [Kokoro TTS](https://hackerapproved.com/p/kokoro-tts.md): 59 recommend - [Pocket TTS](https://hackerapproved.com/p/pocket-tts.md): 41 recommend - [Kitten TTS](https://hackerapproved.com/p/kitten-tts.md): 33 recommend - [Piper TTS](https://hackerapproved.com/p/piper.md): 21 recommend ## Cite as Hacker Approved, "Qwen3-TTS", https://hackerapproved.com/p/qwen3-tts/ (counts from 1,795,640 Hacker News comments, November 2025 to November 2026).