DIFF.BLOG
New Following Discover Jobs
More
Top Writers Suggest a blog Upvotes plugin
Report bug Contact About
Sign up
Topics
Follow your own topics →
Menu
New Following Discover Jobs Top Writers
More
Suggest a blog Upvotes plugin Report bug Contact About
Sign up
The home for great developer writing.
We surface the best developer writing from thousands of independent blogs, updated daily.
Join Diff.blog
TOPICS

Getting speaker: '@' from the gpt-40-transcribe-diarize model

1 · Community Openai · Aug. 4, 2026, 6:01 p.m.
transcription Bug Reporting audio processing GPT-4
Summary
The author discusses encountering a bug with the gpt-40-transcribe-diarize model where a speaker is identified as '@', producing erroneous results not found in the audio file. Key observations highlight issues with the text output and timing of the audio segments.
Read full post on community.openai.com →
MORE POSTS LIKE THIS
Guitar Signals: AC Riding on DC
J. Pereira · Aug 2, 2026
none Electrical Engineering
I Built a Native macOS Transcription App with Codex in Five Days
Muhammad · Jul 28, 2026
AI macos
All the Machines Intros False Memory Real-Time Audio Disintegration Effect
Synthtopia · Jul 30, 2026
All The Machines Audio Effects
Tiny Player for iOS 2.2.1
Catnap Games · Jul 24, 2026
iOS Development audio processing
AI Project: Build a YouTube Video Summarizer (Whisper + Hugging Face)
Ahmed Nabil · Jul 22, 2026
Data Science python projects
AI Project: Build a YouTube Video Summarizer (Whisper + Hugging Face)
Ahmed Nabil · Jul 22, 2026
Data Science python projects
Discover more posts →
AUTHOR
RECENT POSTS FROM THE AUTHOR
Choose how you want to continue.
Continue with GitHub Continue with Google