Code tutorial → https://g.dev/cloud/gemini-3-5-transcribe-github
Code script → https://g.dev/cloud/gemini-3-5-transcribe-live-github
Docs → https://g.dev/cloud/3-5-transcribe-docs
Explore how to build speech-to-text applications using Gemini 3.5 Transcribe models and the Google GenAI SDK. Learn the two primary implementation patterns: synchronous batch processing for pre-recorded audio and low-latency streaming over WebSockets via the Live API. From there, explore essential configuration knobs, such as word-level timestamps, multilingual language codes, speaker diarization, and custom vocabulary biasing to produce highly accurate, production-ready transcriptions.
Chapters:
0:00 – Intro
0:41 – Synchronous & Streaming APIs
1:03 – Client initialization & Model IDs
1:38 – Synchronous transcription pattern
2:12 – Feature 1: Word-level timestamps
2:28 – Feature 2: Language codes
2:46 – Feature 3: Speaker diarization
2:55 – Feature 4: Custom vocabulary biasing
3:09 – Streaming transcription pattern
4:30 – Recap
🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech
#GoogleCloudTech #Gemini
Speaker: Katie Nguyen
Products Mentioned: Gemini Audio, Gemini 3.5 Transcription, Gemini Enterprise
