●MODEL — Gemini 3.5 Flash reaches general availability and becomes gemini-flash-latest●API — The Interactions API hits GA as the primary way to work with Gemini models and agents●AGENT — Managed Agents enter public preview, running stateful agents in isolated Linux sandboxes●API — Background execution lands, letting you fire long-running jobs and collect results later●SEARCH — File Search now embeds and searches images natively via gemini-embedding-2●NOTICE — Since June 19, requests from unrestricted API keys are blocked●MODEL — Gemini 3.5 Flash reaches general availability and becomes gemini-flash-latest●API — The Interactions API hits GA as the primary way to work with Gemini models and agents●AGENT — Managed Agents enter public preview, running stateful agents in isolated Linux sandboxes●API — Background execution lands, letting you fire long-running jobs and collect results later●SEARCH — File Search now embeds and searches images natively via gemini-embedding-2●NOTICE — Since June 19, requests from unrestricted API keys are blocked

TAG

audio-understanding

1 articles

← Back to all tags

gemini-api¹ structured-output¹ indie-dev¹ files-api¹

◈ Gemini API/2026-06-30Advanced

Letting Gemini Listen to a Long Track and Build Its Chapters — Timestamped Structured Extraction

How I replaced hours of hand-chaptering long healing-audio tracks with Gemini's audio understanding: uploading long files via the Files API, pinning JSON output with response_schema, and the validation code that catches audio-specific quirks like timestamp drift and phantom silence.