Tutorial runs Whisper in the browser via Transformers.js for subtitles
11/14/2026 — 11/15, 00:17·1 sources (all)·1 reports (all)
Key takeaways
- A DEV tutorial shows how to run Whisper in the browser with Transformers.js to turn audio into SRT/VTT subtitles while the audio never leave…
Background & analysis
On 2026-11-14, the AI section of DEV Community published a tutorial showing how to run Whisper in a web page with Transformers.js to transcribe audio into SRT or VTT subtitles. According to the tutorial, the entire transcription happens locally on the visitor's machine: the browser downloads the speech model once and caches it, and the audio file never leaves the visitor's computer. There is no need for a server, no API key is required, and there is no per-minute billing.
For the implementation, the tutorial uses a Web Worker to process long audio files in blocks, and it prefers WebGPU for inference while falling back to WASM when WebGPU is not available. The author also lists three issues they actually ran into during development, and the post ends with a working version so that readers can try it out before reading through the code.
At this point the event is covered by this tutorial alone. The public record stops at the tutorial's walkthrough of the implementation approach and the pitfalls the author encountered, with no further development reported.
AI-generated from 1 reports · updated 3 days ago
- Heat index
- 25
- All sources
- 1
- All reports
- 1
- First seen
- 3 days ago
Reports on this story headlines open the original
A DEV tutorial shows how to run Whisper in the browser with Transformers.js and emit SRT/VTT subtitles, keeping the audio on the visitor's machine with no server or API key. It covers a Web Worker for processing long files in blocks, WebGPU with a WASM fallback, and three pitfalls the authors hit.
DEV Community · AIAI score 62
Other stories people are talking about
- Heat index 1336RisingNvidia board not discussing Jensen Huang's return, probe into his conduct advances22 sources
- Heat index 1232RisingCalifornia Sues OpenAI Over Agents Escaping Tests, Intruding into Hugging Face15 sources
- Heat index 894Alibaba releases MoE model Qwen4-Max with 1M token context for low-cost, long-running tasks17 sources
- Heat index 665US Commerce Department issues interim final rule restricting remote access to AI chips via overseas data centers10 sources
- Heat index 528Anthropic to begin trading on Nasdaq this week under ticker ANT9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

