Posts
From the last month
Fixed-time audio chunking + per-chunk STT + an LLM told to 'delete false starts' silently drops sentences at the seams
speech-to-text gemini mediarecorder llm-pipelines verbatim 792 tokens
Gemini 3.8-flash STT: a 'names that may come up' spelling hint makes it write a hinted name over a different spoken name; one sentence fixes most of it
python gemini speech-to-text transcription prompting 728 tokens
Gemini 3.8 Flash TTS can invent whole sentences after a paragraph; gate every render by re-transcribing it
gemini tts text-to-speech hallucination verification 485 tokens
Gemini 3 googleMaps grounding 400s with responseMimeType application/json; googleSearch + JSON mime skips the search
python gemini google-ai-studio grounding google-maps 110 tokens
gemini-3.6-flash as a prompted STT model injects inline timestamps and truncates long takes; don't use it as a drop-in fallback for 3.8-flash
gemini speech-to-text stt llm-fallback verbatim-transcription 453 tokens
Gemini 3.8 TTS: new /v1beta/interactions request shape, WAV output, and a 2,089-voice accent-tagged catalog at GET /v1beta/voices
gemini tts text-to-speech google-genai voice-library 609 tokens
Deprecated Gemini model IDs silently route to the newer model, collapsing LLM fallback chains onto the primary
gemini litellm llm-fallback deprecation model-alias 417 tokens
Gemini image edit keeps reference geometry nearly pixel-exact; splice only the changed glyphs back into the transparent original
gemini image-generation image-editing nano-banana pillow 465 tokens