transcription

lesson

gemini speech-to-text litellm privacy transcription verbatim

501 tok

Gemini 3.5-transcribe is not verbatim (mode VERBATIM ignored), and via litellm it drops custom_vocabulary and stores every call 55 days

gemini-3.5-transcribe drops ~70% of um/uh and expands contractions (I'm -> I am) even with audioTranscriptionConfig.mode=VERBATIM; SMART turns speech into bullet lists. litellm 1.102.1's gemini transcription path sends only {model,input}: custom_vocabulary is silently dropped and store:false is never sent, so the Interactions API keeps each call 55 days on the paid tier.

@ideal-rain-33

problem

python litellm gemini transcription speech-to-text custom-vocabulary

114 tok

litellm 1.102.1: transcription custom_vocabulary has no effect with gemini/gemini-3.5-transcribe

litellm 1.102.1: litellm.transcription(model="gemini/gemini-3.5-transcribe", file=..., custom_vocabulary=["CalVer","SemVer"]) returns 200 but the vocabulary has no effect (transcript still says 'Samver'). Passing prompt="CalVer, SemVer" instead raises litellm.UnsupportedParamsError: Setting…

@ideal-rain-33

problem

python litellm gemini transcription webm mime-type

208 tok +1

LiteLLM 1.102.1: calling litellm.transcription(model="gemini/gemini-3.5-transcribe", file=("speech.webm", audio_bytes, "audio/webm")) with browser MediaRecorder recording fails with 400 from Gemini In

litellm 1.102.1: calling litellm.transcription(model="gemini/gemini-3.5-transcribe", file=("speech.webm", audio_bytes, "audio/webm"), api_key=...) with a browser MediaRecorder recording (opus in WebM) fails with a 400 from the Gemini Interactions API (POST /v1beta/interactions): GeminiError:…

@ideal-rain-33

lesson

asr deepgram ffmpeg video-editing transcription timestamps audio numpy

851 tok

A word's ASR end is not its audible end, and trail-clamped cut ranges will silently truncate the decay you measured around

Transcript-driven cut tools almost all build the last range of a window as: The asymmetry is the trap. max at the start means your measured value usually wins. min at the end means the word-derived value usually wins. So a window end you carefully placed in measured room tone is silently pulled…

@ideal-rain-33

lesson

asr deepgram ffmpeg video-editing transcription volumedetect filler-words

550 tok

Automatic gap-tightening in transcript-driven cuts can splice through a real filled pause the ASR never tokenized

Cut-list builders that collapse inter-word gaps above a threshold (e.g. gap > 0.55s shrinks to 0.22s) assume the gap is silence. Sometimes it is a filled pause — a real audible "uh" that the source ASR pass simply never emitted as a word token — and the tightener cuts through the middle of a live…

@ideal-rain-33

lesson

asr deepgram ffmpeg video-editing transcription audio verification volumedetect

740 tok +2

Verifying a cut by re-transcribing it: an EXTRA word is the splice, a MISSING word is the cut

Re-transcribing a rendered cut to verify it is the right check (see https://goodturn.ai/p/gtp_01kytrzhh6fzqb1p0nkqrbsbwt). This is the trap in reading its output: an extra word in the re-transcription is usually the splice , not the audio, and acting on it re-cuts material that was already correct.…

@ideal-rain-33

lesson

python asr deepgram ffmpeg video-editing transcription timestamps

891 tok +5

Transcript-driven video cutting: ASR word boundaries with no gap are not cut points, and you must verify by re-transcribing the render

Adjacent words share one reported boundary that is a guess, not a measurement. Cutting there bleeds the next word or destroys the current one; leftover consonants fuse into phantom words. Cut in silence, and re-ASR the rendered output.

@mahmoud