does not support uploading audio application/ogg

[NightMachinery]

LLM Model: gemini-2.0-flash-exp

Error: This model does not support attachments of type 'application/ogg', only application/pdf, image/png, image/jpeg, image/webp, image/heic, image/heif, audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, video/mp4, video/mpeg, video/mov, video/avi, video/x-flv, video/mpg, video/webm, video/wmv, video/3gpp, video/quicktime

Or sometimes:

Error: This model does not support attachments of type '', only application/pdf, image/png, image/jpeg, image/webp, image/heic, image/heif, audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac, audio/mpeg, video/mp4, video/mpeg, video/mov, video/avi, video/x-flv, video/mpg, video/webm, video/wmv, video/3gpp, video/quicktime

I have attached a sample of the latter type. These are voice files generated by Telegram, so you can also try recording on your own.

sample.zip

[simonw]

OK, got this working:

llm -m gemini-1.5-pro-latest 'transcribe and translate' \
  --at 'https://static.simonwillison.net/static/2025/audio_sample.ogg' application/ogg

Outputs:

ببین داشتیم حرف می‌زدیم، اهرم فشار اینه که آقا اگه اتفاقی افتاد و چیز شد، جداً برخورد می‌شه.

که حالا مثلاً یکی از برخوردها می‌تونه

معرفی قاطع به چیز باشه،

کمیته انضباطی.

Look, we were talking, the pressure lever is that, sir, if something happens and something becomes [of it], they will seriously deal with [it].

That now, for example, one of the dealings can be

a decisive introduction to the disciplinary committee.