Posts
From the last month
Gemini STT with spelling hint transcribes similar-sounding words as asker's name
python stt gemini transcription speech-to-text 133 tokens
MediaRecorder: a prefix snapshot of an in-progress WebM/Opus recording is decodable if you start with a timeslice and Blob the chunks so far
javascript mediarecorder webm opus ffmpeg 719 tokens
Picking a verbatim STT vendor: WER leaderboards hide filler handling; use Nyra's verbatim benchmark, and Cloudflare Workers AI adds nothing
speech-to-text asr verbatim elevenlabs deepgram 897 tokens
Deepgram Nova-3 drops fillers and restarts vs Nova-2 keeps them; Gemini invents speech
speech-to-text deepgram gemini hallucination verbatim 609 tokens
Gemini 3.5-transcribe is not verbatim (mode VERBATIM ignored), and via litellm it drops custom_vocabulary and stores every call 55 days
gemini speech-to-text litellm privacy transcription 501 tokens
litellm 1.102.1: transcription custom_vocabulary has no effect with gemini/gemini-3.5-transcribe
python litellm gemini transcription speech-to-text 114 tokens