Voilà Pro adds offline live input powered by local Whisper and Qwen
10/30/2026 — 10/30, 21:19·1 sources (all)·1 reports (all)
Key takeaways
- The developer of Voilà Pro announced that the app now supports offline live input, swapping cloud models for local Whisper and Qwen and hand…
Background & analysis
On October 30, 2026, the developer of Voilà Pro posted on V2EX to announce a new release built around offline, real-time input. The developer explained that Voilà Pro's mixed input previously relied on network-based models, but many users wanted to keep everything local and avoid sending data to the cloud, and the cloud-dependent setup was also unfriendly to users in mainland China. Offline options were limited: Apple's on-device transcription was described as slow and inaccurate, and most existing offline input tools were said to remain stuck at the transcription level. In response, the new version swaps in local Whisper and Qwen models, enabling real-time input and mixed input entirely on-device, with Chinese, English, French, and other languages being entered simultaneously. An offline API is also offered, capable of calling servers that are compatible with OpenAI. The developer noted that Voilà Pro was originally written in Swift from scratch, and that the new interface was a collaboration between a self-described "genius programmer" and the Voilà team, bringing major visual changes. Early-bird licenses sold previously still work, since activation is handled offline. The post ends with the phrase "Key point: only supports," but the excerpt provided does not spell out the exact compatibility scope.
AI-generated from 1 reports · updated 13 hours ago
Related AI tools
- Heat index
- 67
- All sources
- 1
- All reports
- 1
- First seen
- 14 hours ago
Reports on this story headlines open the original
The developer of Voilà Pro has released an update that enables offline real-time input using local models instead of network models. Users can type in Chinese, English, French and other languages simultaneously, and the app can also call OpenAI-compatible offline APIs.
V2EXAI score 57
Other stories people are talking about
- Heat index 77Community benchmarks DFlash2 draft model for Qwen3.8-Flash-Next1 sources
- Heat index 51Developer compiles a RISC-V CPU into Qwen3.5-4B weights1 sources
- Heat index 74Running Qwen-Image 2.1 Turbo offline with step-by-step previews1 sources
- Heat index 1010NewApple Intelligence comes to China with Qwen inside Siri11 sources
- Heat index 861RisingAlphabet plunges nearly 13% in one day, shedding about $500 billion in market value19 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

