Using Codex to Improve Voice-to-Text: Auto-Extracting Custom Vocabularies
jdjohnson · x · 2026-08-01
Shares a practical workflow to improve voice-to-text accuracy. The author suggests using Codex to analyze a user's past conversations, Slack messages, and emails to automatically extract frequently used domain-specific words and phrases into a spreadsheet. This vocabulary list can then be imported into the dictation tool Superwhisper to significantly reduce recognition errors for proper nouns.
More from coding & agent
- Vercel AI Gateway Adds Team and Project Spend Budgets — cramforce · 2026-08-01
- Developer Demos Vibe Coding Workflow: Build and Ship Apps in 30 Minutes — vista8 · 2026-08-01
- GitHub Hit: DNS-Only Feed Reader and E2EE Messenger for Censored Networks — tom_doerr · 2026-08-01
- Dev Showcases Local Multimodal AI Companion App Running on RTX 4060 Ti — aziib · 2026-08-01
- Conductor in Action: Orchestrating Autonomous Agents from a Single Workspace — charlieholtz · 2026-08-01
- Cisco AI Launches Antares Quickstart Guide for 15-Minute Code Vulnerability Localization — aminkarbasi · 2026-08-01