
What happened
He sent a 10-line script plus a 'play a capable secretary' tone instruction to Gemini's TTS model (voice Laomedeia) in one call; the resulting 62.7-second audio opened with about 15 seconds of the instruction being read aloud, and after cutting it the script portion ran 47.7 seconds.
Why it matters
He caught the problem by running the audio through faster-whisper transcription, which is already part of his pipeline as an automatic check that the audio matches the script — so a leaked instruction would lower the match score and be noticed.
Summaries like this, every morning.
The experiment grew out of a small, repeated workflow: an engineer who holds daily meetings with AI executive personas turns each session into a roughly one-minute video. Until now the voice was made by hand — extracting audio from a video generated with Gemini — so script-to-voice was never a single step. The proposal to call the TTS API directly came from his CTO-role AI, and the appeal was precisely that it could go from script to voice in one pass.
Two design choices shaped what happened next. Rather than calling the model ten times, once per line, he sent all ten lines in a single call, on the view that a per-line approach tends to shift the voice's tone from call to call; per-line timing would instead be recovered afterward from transcription. And because the model received the tone instruction alongside the script, it treated both as text to be read — which is how roughly 15 seconds of instruction ended up at the head of a 62.7-second file, leaving 47.7 seconds of script after the trim.
The transcription step is what makes the failure detectable rather than silent: it was already slated to serve as an automatic 90%-or-better match check against the script, and a leaked instruction lowers that score. Open questions remain — the whole flow is still a draft awaiting his sign-off, and the split-field fix is untested.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Softsu announced that its AI phone auto-response service Mirai AI received the AX Contribution Award in the AI…

Testing phonon:31m-en, the tester got English short-sentence audio in 0.2–0.3 seconds and long-sentence audio…

Amazon Polly voice cloning is now generally available as a gated release, building a custom voice from 1–10 re…

OpenAI is rolling out Live Dictation globally on all ChatGPT plans across web, desktop, iOS and Android; it tr…

StudyPocket released "AI Interview Prep - Mock Interviews with Voice" for iOS and Android on November 19, a fr…

The narrator's preschool-attending son became hooked on videos of animals and dinosaurs fighting one-on-one, a…
