{"slug": "qwen-asr", "name": "Qwen ASR", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 6, "commenters": 6, "warners": 0, "score": 5.53, "rising": 2.02, "first": "2026-02-27", "latest": "2026-10-20", "why": "Qwen-asr can easily transcribe live radio (see README) in any random laptop.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 6, "neutral": 0, "compare": 0, "warn": 0}, "spark": [0, 0, 0, 1, 2, 0, 0, 0, 0, 1, 0, 2], "listed": true, "loved": [], "caveat": "", "short_quote": "Qwen-asr can easily transcribe live radio (see README) in any random laptop.", "kind": "", "icon": false, "domain": null, "github_repo": "github.com/antirez/qwen-asr", "official_url": "https://github.com/antirez/qwen-asr", "pricing": "", "aliases": ["Qwen ASR", "qwen-asr", "Qwen-ASR"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 802710705, "item_id": 50169419, "url": "https://news.ycombinator.com/item?id=50169419", "by": "dr_hooo", "date": "2026-10-20", "stance": "recommend", "quote": "I found Qwen ASR and QwenTTS to be quite good", "excerpt": "Too bad it's not open, unlike the previous version. However, I found Qwen ASR and QwenTTS to be quite good, and not too large. Also https://github.com/kyutai-labs/pocket-tts was also great (but only a few languages)", "context": "", "use_case": "", "switched_from": "", "story": "Voxtral 3"}, {"id": 800186129, "item_id": 50011633, "url": "https://news.ycombinator.com/item?id=50011633", "by": "skolos", "date": "2026-10-08", "stance": "recommend", "quote": "qwen recognized correctly 168", "excerpt": "Interesting that this is here. I used whistle (and bunch of other things) to take ownership of my echo show. It now doesn't dial to Amazon at all - it does all processing locally with its own CPU and connects to my homeassistant for home automation. My initial setup involved qwen asr (1.7b model) running on rtx 5080. Compared to that, whistle was really bad (out of 170 messages, qwen recognized correctly 168, whistle", "context": "has a heavy accent", "use_case": "local speech recognition", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 790500865, "item_id": 49406304, "url": "https://news.ycombinator.com/item?id=49406304", "by": "loveparade", "date": "2026-08-23", "stance": "recommend", "quote": "give it to qwen asr for raw transcription", "excerpt": "I built my own pipeline for this because in my experience the YouTube auto transcripts are quite bad. I download the raw audio track with yt-dlp, give it to qwen asr for raw transcription, then DeepSeek flash for transcription cleanup, formatting, corrections with web search enabled, etc. I use openrouter to call the models. It's a few cents per video (mostly the asr model at ~12 cents per hour) and quality is great.", "context": "", "use_case": "audio transcription", "switched_from": "", "story": "Ask HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT?"}, {"id": 761467488, "item_id": 47591718, "url": "https://news.ycombinator.com/item?id=47591718", "by": "atoav", "date": "2026-03-31", "stance": "recommend", "quote": "I would try Qwen-ASR: https://qwen.ai/blog?id=qwen3asr", "excerpt": "I would try Qwen-ASR: https://qwen.ai/blog?id=qwen3asr See the very bottom of the page for a transcription with timestamps.", "context": "", "use_case": "", "switched_from": "", "story": "Cohere Transcribe: Speech Recognition"}, {"id": 758475206, "item_id": 47404700, "url": "https://news.ycombinator.com/item?id=47404700", "by": "bachittle", "date": "2026-03-16", "stance": "recommend", "quote": "Qwen ASR and TTS are really good.", "excerpt": "Coqui TTS is actually deprecated, the company shut down. I have a voice assistant that is using gpt-5.4 and opus 4.6 using the subsidized plans from Codex and Claude Code, and it uses STT and TTS from mlx-audio for those portions to be locally hosted: https://github.com/Blaizzy/mlx-audio Here are the following models I found work well: - Qwen ASR and TTS are really good. Qwen ASR is faster than OpenAI Whisper on Appl", "context": "", "use_case": "speech recognition", "switched_from": "", "story": "My Journey to a reliable and enjoyable locally hosted voice assistant"}]}], "caveats": [], "who": [{"by": "skolos", "context": "has a heavy accent", "url": "https://news.ycombinator.com/item?id=50011633", "date": "2026-10-08"}], "tags": [], "use_cases": ["local speech recognition", "audio transcription", "speech recognition"], "compared": [{"slug": "qwen-tts", "name": "Qwen TTS", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=50168396", "title": "Voxtral 3", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50008427", "title": "Whistle: Speech to Text in 16.9 MB", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49405684", "title": "Ask HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47589818", "title": "Cohere Transcribe: Speech Recognition", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47398534", "title": "My Journey to a reliable and enjoyable locally hosted voice assistant", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=47176239", "title": "Parakeet.cpp \u2013 Parakeet ASR inference in pure C++ with Metal GPU acceleration", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"recommend": 1}, "2026-03": {"recommend": 2}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {"recommend": 2}}, "quotes": [{"id": 802710705, "item_id": 50169419, "url": "https://news.ycombinator.com/item?id=50169419", "by": "dr_hooo", "date": "2026-10-20", "stance": "recommend", "quote": "I found Qwen ASR and QwenTTS to be quite good", "excerpt": "Too bad it's not open, unlike the previous version. However, I found Qwen ASR and QwenTTS to be quite good, and not too large. Also https://github.com/kyutai-labs/pocket-tts was also great (but only a few languages)", "context": "", "use_case": "", "switched_from": "", "story": "Voxtral 3"}, {"id": 800186129, "item_id": 50011633, "url": "https://news.ycombinator.com/item?id=50011633", "by": "skolos", "date": "2026-10-08", "stance": "recommend", "quote": "qwen recognized correctly 168", "excerpt": "Interesting that this is here. I used whistle (and bunch of other things) to take ownership of my echo show. It now doesn't dial to Amazon at all - it does all processing locally with its own CPU and connects to my homeassistant for home automation. My initial setup involved qwen asr (1.7b model) running on rtx 5080. Compared to that, whistle was really bad (out of 170 messages, qwen recognized correctly 168, whistle", "context": "has a heavy accent", "use_case": "local speech recognition", "switched_from": "", "story": "Whistle: Speech to Text in 16.9 MB"}, {"id": 790500865, "item_id": 49406304, "url": "https://news.ycombinator.com/item?id=49406304", "by": "loveparade", "date": "2026-08-23", "stance": "recommend", "quote": "give it to qwen asr for raw transcription", "excerpt": "I built my own pipeline for this because in my experience the YouTube auto transcripts are quite bad. I download the raw audio track with yt-dlp, give it to qwen asr for raw transcription, then DeepSeek flash for transcription cleanup, formatting, corrections with web search enabled, etc. I use openrouter to call the models. It's a few cents per video (mostly the asr model at ~12 cents per hour) and quality is great.", "context": "", "use_case": "audio transcription", "switched_from": "", "story": "Ask HN: Anyone set up ways to easily obtain and read transcripts from Ted, YT?"}, {"id": 761467488, "item_id": 47591718, "url": "https://news.ycombinator.com/item?id=47591718", "by": "atoav", "date": "2026-03-31", "stance": "recommend", "quote": "I would try Qwen-ASR: https://qwen.ai/blog?id=qwen3asr", "excerpt": "I would try Qwen-ASR: https://qwen.ai/blog?id=qwen3asr See the very bottom of the page for a transcription with timestamps.", "context": "", "use_case": "", "switched_from": "", "story": "Cohere Transcribe: Speech Recognition"}, {"id": 758475206, "item_id": 47404700, "url": "https://news.ycombinator.com/item?id=47404700", "by": "bachittle", "date": "2026-03-16", "stance": "recommend", "quote": "Qwen ASR and TTS are really good.", "excerpt": "Coqui TTS is actually deprecated, the company shut down. I have a voice assistant that is using gpt-5.4 and opus 4.6 using the subsidized plans from Codex and Claude Code, and it uses STT and TTS from mlx-audio for those portions to be locally hosted: https://github.com/Blaizzy/mlx-audio Here are the following models I found work well: - Qwen ASR and TTS are really good. Qwen ASR is faster than OpenAI Whisper on Appl", "context": "", "use_case": "speech recognition", "switched_from": "", "story": "My Journey to a reliable and enjoyable locally hosted voice assistant"}, {"id": 754847985, "item_id": 47177999, "url": "https://news.ycombinator.com/item?id=47177999", "by": "antirez", "date": "2026-02-27", "stance": "recommend", "quote": "Qwen-asr can easily transcribe live radio (see README) in any random laptop.", "excerpt": "Related: https://github.com/antirez/qwen-asr https://github.com/antirez/voxtral.c Qwen-asr can easily transcribe live radio (see README) in any random laptop. It looks like we are going to see really cool things on local inference, now that automatic programming makes a lot simpler to create solid pipelines for new models in C, C++, Rust, ..., in a matter of hours.", "context": "", "use_case": "", "switched_from": "", "story": "Parakeet.cpp \u2013 Parakeet ASR inference in pure C++ with Metal GPU acceleration"}]}