{"slug": "voxtral", "name": "Voxtral", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 6, "warners": 2, "score": 1.222, "rising": 0.35, "first": "2026-02-08", "latest": "2026-09-08", "why": "No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 1, "compare": 0, "warn": 2}, "spark": [0, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts.", "icon": false, "domain": null, "github_repo": null, "official_url": "", "pricing": "", "aliases": ["Voxtral"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 791650226, "item_id": 49478139, "url": "https://news.ycombinator.com/item?id=49478139", "by": "decide1000", "date": "2026-08-28", "stance": "recommend", "quote": "In my tests with other languages Voxtral was better then Whisper.", "excerpt": "I use Whisper in combination with Qwen3.8 27b to create Dutch subtitles for Russian videos. I follow Ukrainian channels about the war and I am now able to understand them. In my tests with other languages Voxtral was better then Whisper. Whisper often makes mistakes which I now solve with an extra layer (qwen). Sadly Mistral does not support Ukrainian. I hope this changes! I expect better from a European model", "context": "", "use_case": "speech transcription", "switched_from": "", "story": "Gemini-3.5-Transcribe"}, {"id": 782331760, "item_id": 48895735, "url": "https://news.ycombinator.com/item?id=48895735", "by": "summarity", "date": "2026-07-13", "stance": "recommend", "quote": "No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts.", "excerpt": "Vs Voxtral would be a better comparison. No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts. Seems to understand/infer all the technobabble I use at work. Never have to edit anything. Whisper was catastrophically bad.", "context": "", "use_case": "meeting transcription", "switched_from": "Whisper", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 750985649, "item_id": 46936603, "url": "https://news.ycombinator.com/item?id=46936603", "by": "k9294", "date": "2026-02-08", "stance": "recommend", "quote": "I personally switched to it as my main default fast model - it's really good.", "excerpt": "Hey, I would really appreciate if you would try https://ottex.ai I'm working on a Wispr/Spokenly competitor. It's free without any paywalled features, supports local models and a bunch of API providers including Mistral. For local models ottex has - parakeet V3, Whisper, GLM-ASR nano, Qwen3-ASR (don't have voxtral yet though, looking into it). btw, you can try new voxtral model via API (the model name to pick is `vox", "context": "", "use_case": "fast transcription model", "switched_from": "", "story": "Voxtral Transcribe 2"}, {"id": 750984593, "item_id": 46936537, "url": "https://news.ycombinator.com/item?id=46936537", "by": "k9294", "date": "2026-02-08", "stance": "recommend", "quote": "I personally switched to it as my main default fast model - it's really good.", "excerpt": "Hey, I would really appreciate if you will try https://ottex.ai I'm working on a Wispr/Spokenly competitor. It's free without any paywalled features, supports local models and bunch of API providers including Mistral. btw, the model name to pick is `voxtral-mini-latest:transcribe`, I personally switched to it as my main default fast model - it's really good.", "context": "", "use_case": "fast transcription", "switched_from": "", "story": "Voxtral Transcribe 2"}, {"id": 750983617, "item_id": 46936476, "url": "https://news.ycombinator.com/item?id=46936476", "by": "k9294", "date": "2026-02-08", "stance": "recommend", "quote": "model is actually a very good one, I personally switched to it as my default model.", "excerpt": "Try https://ottex.ai/ I recently added support for Mistral provider, model is actually a very good one, I personally switched to it as my default model. p.s. the app is free for personal user, has support for both local models and BYOK with OpenRouter, Groq, Mistral, Fireworks, and more coming soon.", "context": "", "use_case": "transcription", "switched_from": "", "story": "Voxtral Transcribe 2"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 791599410, "item_id": 49474963, "url": "https://news.ycombinator.com/item?id=49474963", "by": "jwr", "date": "2026-08-28", "stance": "warn", "quote": "I tried the larger Voxtral models, but they didn't work for me at all.", "excerpt": "It's interesting that the results can be so different depending on the person, the use case and even the microphone used. I use dictation a lot, so I try to stay up to date with the latest models as much as I can. So far, for my needs, nothing could beat Whisper Large v3. I keep hearing that Nvidia Parakeet models are better, but they just don't work as well for me, even though they are unquestionably faster. Things ", "context": "", "use_case": "multilingual dictation", "switched_from": "", "story": "Gemini-3.5-Transcribe"}, {"id": 751347490, "item_id": 46959218, "url": "https://news.ycombinator.com/item?id=46959218", "by": "d4rkp4ttern", "date": "2026-02-10", "stance": "warn", "quote": "I tried incorporating this Voxtral C implementation into Handy but got very slow transcriptions on my M1 Max MacBook 64GB.", "excerpt": "I use the open source Handy [1] app with Parakeet V3 for STT when talking to coding agents and I\u2019ve yet to see anything that beats this setup in terms of speed/accuracy. I get near instant transcription, and the slight accuracy drop is immaterial when talking to AIs that can \u201cread between the lines\u201d. I tried incorporating this Voxtral C implementation into Handy but got very slow transcriptions on my M1 Max MacBook 6", "context": "", "use_case": "speech-to-text", "switched_from": "", "story": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model"}]}], "who": [], "tags": [], "use_cases": ["speech transcription", "multilingual dictation", "meeting transcription", "speech-to-text", "fast transcription model", "fast transcription"], "compared": [{"slug": "whisper", "name": "Whisper", "co": 2, "switched_from": 1, "switched_to": 0}, {"slug": "parakeet", "name": "Parakeet", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "wispr-flow", "name": "Wispr Flow", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "handy", "name": "Handy", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "spokenly", "name": "Spokenly", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=46886735", "title": "Voxtral Transcribe 2", "mentions": 3}, {"url": "https://news.ycombinator.com/item?id=49468818", "title": "Gemini-3.5-Transcribe", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=49605767", "title": "Mistral raises \u20ac3B", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48894752", "title": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46954049", "title": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model", "mentions": 1}], "sentiment_by_month": {"2025-11": {}, "2025-12": {}, "2026-01": {}, "2026-02": {"recommend": 1, "warn": 1}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"recommend": 1}, "2026-08": {"warn": 1, "recommend": 1}, "2026-09": {"neutral": 1}, "2026-10": {}}, "quotes": [{"id": 793835362, "item_id": 49614710, "url": "https://news.ycombinator.com/item?id=49614710", "by": "moffkalast", "date": "2026-09-08", "stance": "neutral", "quote": "Except Voxtral perhaps, but that's very niche.", "excerpt": "I don't think any Mistral model can match an open 30B-sized Qwen from a year ago, so right now they're not really a competitive alternative to anything at all. Except Voxtral perhaps, but that's very niche.", "context": "", "use_case": "", "switched_from": "", "story": "Mistral raises \u20ac3B"}, {"id": 791650226, "item_id": 49478139, "url": "https://news.ycombinator.com/item?id=49478139", "by": "decide1000", "date": "2026-08-28", "stance": "recommend", "quote": "In my tests with other languages Voxtral was better then Whisper.", "excerpt": "I use Whisper in combination with Qwen3.8 27b to create Dutch subtitles for Russian videos. I follow Ukrainian channels about the war and I am now able to understand them. In my tests with other languages Voxtral was better then Whisper. Whisper often makes mistakes which I now solve with an extra layer (qwen). Sadly Mistral does not support Ukrainian. I hope this changes! I expect better from a European model", "context": "", "use_case": "speech transcription", "switched_from": "", "story": "Gemini-3.5-Transcribe"}, {"id": 791599410, "item_id": 49474963, "url": "https://news.ycombinator.com/item?id=49474963", "by": "jwr", "date": "2026-08-28", "stance": "warn", "quote": "I tried the larger Voxtral models, but they didn't work for me at all.", "excerpt": "It's interesting that the results can be so different depending on the person, the use case and even the microphone used. I use dictation a lot, so I try to stay up to date with the latest models as much as I can. So far, for my needs, nothing could beat Whisper Large v3. I keep hearing that Nvidia Parakeet models are better, but they just don't work as well for me, even though they are unquestionably faster. Things ", "context": "", "use_case": "multilingual dictation", "switched_from": "", "story": "Gemini-3.5-Transcribe"}, {"id": 782331760, "item_id": 48895735, "url": "https://news.ycombinator.com/item?id=48895735", "by": "summarity", "date": "2026-07-13", "stance": "recommend", "quote": "No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts.", "excerpt": "Vs Voxtral would be a better comparison. No other model, open or closed, has been able to hit such a low AER (Acronym Error Rate ;)) for my meeting transcripts. Seems to understand/infer all the technobabble I use at work. Never have to edit anything. Whisper was catastrophically bad.", "context": "", "use_case": "meeting transcription", "switched_from": "Whisper", "story": "Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor"}, {"id": 751347490, "item_id": 46959218, "url": "https://news.ycombinator.com/item?id=46959218", "by": "d4rkp4ttern", "date": "2026-02-10", "stance": "warn", "quote": "I tried incorporating this Voxtral C implementation into Handy but got very slow transcriptions on my M1 Max MacBook 64GB.", "excerpt": "I use the open source Handy [1] app with Parakeet V3 for STT when talking to coding agents and I\u2019ve yet to see anything that beats this setup in terms of speed/accuracy. I get near instant transcription, and the slight accuracy drop is immaterial when talking to AIs that can \u201cread between the lines\u201d. I tried incorporating this Voxtral C implementation into Handy but got very slow transcriptions on my M1 Max MacBook 6", "context": "", "use_case": "speech-to-text", "switched_from": "", "story": "Pure C, CPU-only inference with Mistral Voxtral Realtime 4B speech to text model"}, {"id": 750985649, "item_id": 46936603, "url": "https://news.ycombinator.com/item?id=46936603", "by": "k9294", "date": "2026-02-08", "stance": "recommend", "quote": "I personally switched to it as my main default fast model - it's really good.", "excerpt": "Hey, I would really appreciate if you would try https://ottex.ai I'm working on a Wispr/Spokenly competitor. It's free without any paywalled features, supports local models and a bunch of API providers including Mistral. For local models ottex has - parakeet V3, Whisper, GLM-ASR nano, Qwen3-ASR (don't have voxtral yet though, looking into it). btw, you can try new voxtral model via API (the model name to pick is `vox", "context": "", "use_case": "fast transcription model", "switched_from": "", "story": "Voxtral Transcribe 2"}, {"id": 750984593, "item_id": 46936537, "url": "https://news.ycombinator.com/item?id=46936537", "by": "k9294", "date": "2026-02-08", "stance": "recommend", "quote": "I personally switched to it as my main default fast model - it's really good.", "excerpt": "Hey, I would really appreciate if you will try https://ottex.ai I'm working on a Wispr/Spokenly competitor. It's free without any paywalled features, supports local models and bunch of API providers including Mistral. btw, the model name to pick is `voxtral-mini-latest:transcribe`, I personally switched to it as my main default fast model - it's really good.", "context": "", "use_case": "fast transcription", "switched_from": "", "story": "Voxtral Transcribe 2"}, {"id": 750983617, "item_id": 46936476, "url": "https://news.ycombinator.com/item?id=46936476", "by": "k9294", "date": "2026-02-08", "stance": "recommend", "quote": "model is actually a very good one, I personally switched to it as my default model.", "excerpt": "Try https://ottex.ai/ I recently added support for Mistral provider, model is actually a very good one, I personally switched to it as my default model. p.s. the app is free for personal user, has support for both local models and BYOK with OpenRouter, Groq, Mistral, Fireworks, and more coming soon.", "context": "", "use_case": "transcription", "switched_from": "", "story": "Voxtral Transcribe 2"}]}