Whisper (OpenAI)
“Robust Speech Recognition via Large-Scale Weak Supervision”
by OpenAI
Our review
Whisper is OpenAI's open-source speech-to-text model. Developers run it locally or on servers to transcribe and translate audio in many languages, including very long files.
Pros
- Free and private when run locally
- Many languages
Cons
- Requires technical setup
Being used for
- Transcribing audio and video35 posts · X · HN · X
- Captions and subtitles5 posts · X · HN · HN
- Translating text4 posts · X · HN · HN
Based on 41 public posts on X and Hacker News that describe using it · checked Oct 23, 2026
Also does
CodeGood fit
A Python library and model developers build transcription into apps with.
Limitations
- Code: A building block for developers, not an AI coding assistant.
Use cases · Hear from users
Real posts from people using Whisper (OpenAI) on X, sorted by engagement (English first).
Let's go, 200% faster Whisper w/ speculative decoding! 🔥 Whisper (baseline) - 73 seconds Whisper w/ Speculative Decoding - 33 seconds All with zero drop in performance! ⚡ Pseudocode: 1. Initialise a Teacher model ex: openai/whisper-large-v2. 2. Load an assistant model ex: dis…
726 likes · 107 reposts · 19 repliesView on X ↗Been using Whisper Large to write most of my messages in Slack/Discord today. What a phenomenal piece of software. By the end of the day I had stopped proof reading it, I just hit send. It was almost always fully correct, including capitalisation, acronyms, and punctuation.
8 likes · 0 reposts · 1 repliesView on X ↗I built a player that writes subtitles before the scene arrives. Using Whisper large-v3, on the Apple GPU Link in comments👇 https://t.co/nTQWTTCYX0
4 likes · 1 reposts · 1 repliesView on X ↗i used openai whisper model in a VPS with enough memory to handle self-attention (the mp3 was 4h long) then prompted claude to get a precise prompt meeting my requirements to summarise the txt file. fed that prompt to claude opus 4.1 and sort of cleaned it up best i could h…
5 likes · 0 reposts · 1 repliesView on X ↗I have been using @OpenAI Whisper model to generate English subtitles from my Nepali Devlog videos. It doesn't give a 100% correct output but gives .srt with proper timestamps to get started with finalizing the subtitle. It's amazing!! DevLog #2: https://t.co/odVmyZr6LF
2 likes · 1 reposts · 1 repliesView on X ↗Building scalable AI applications with @Cloudflare Workers AI is fast, straight forward and amazing. I built a transcription app this weekend with Workers AI, R2 and Openai whisper model.
5 likes · 0 reposts · 0 repliesView on X ↗
Show 4 more posts ›Show fewer
I found out that AI transcription can now be done locally with amazing result. Some libraries you might find interesting: - Whisper.cpp: Port of OpenAI Whisper Model in C/C++ - Whisper ggml models - TinyDiarize: Extension of OpenAI Whisper model with speaker diarization!
1 likes · 0 reposts · 1 repliesView on X ↗I’ve been using Whisper typing, built on OpenAI’s Whisper model, and it’s honestly amazing! It picks up almost every word I say. Super accurate. Super smooth. I can’t wait until this works on phones across every app. https://t.co/MBkLAOOREa
0 likes · 0 reposts · 1 repliesView on X ↗Cannot believe I've only just discovered how cool the @OpenAI whisper model is. Is this what all those transcription tools are using behind the scenes? https://t.co/2ib4i9nYgU
1 likes · 0 reposts · 0 repliesView on X ↗I tried OpenAi whisper model for speech to text generation, got to know that its tiny model takes around 500 MB of RAM and the result was worse than android built in speech recognition,
0 likes · 0 reposts · 0 repliesView on X ↗
Related tools
Compare with Descript ›Descript
45Edit video and podcasts by editing the transcript.
ElevenLabs
82The most natural AI voices, voice cloning and dubbing.
Mistral Vibe
70Mistral's chat assistant and coding agent (formerly Le Chat).
Krisp
53Noise cancellation and meeting notes for every call.