Streaming Gemini TTS: concatenate the PCM, write the WAV header once
Streamed Gemini TTS does not arrive as an audio file. It arrives as raw PCM fragments. Here is what happens when you wrap each fragment in its own WAV header, measured on my machine, plus the receiving code that avoids it.
When Streaming Responses Quietly Lose Non-ASCII Text: Measuring the Byte Boundary and the Event Boundary Separately
I measured why Japanese text disappears from streaming Gemini responses using a local mock SSE server. Two separate layers were broken, one of them silently, and an English-only test suite caught neither.
A Gemini stream drops halfway — restart it, or have the model continue?
Most apps silently restart a dropped stream. Here is the arithmetic behind continuing from the partial output instead, and where to put the threshold.
Render Structured Output Field by Field as It Streams: Safe Partial JSON Parsing
With responseSchema streaming, the screen stays blank until the JSON closes. This walks through a partial parser that safely completes unclosed JSON, plus anti-flicker fencing that never lets a field move backward, and shows how time-to-first-field dropped from about 2.4s to 0.4s in practice.
Stop Making Listeners Wait for the Whole File — Wiring Gemini TTS Streaming into Your Delivery Path
gemini-3.1-flash-tts-preview now streams audio via streamGenerateContent. A delivery path with 1.8s to first sound, covering PCM boundary handling, sentence-level resume, and a fallback for preview shutdown.
Gemini API × TypeScript Type-Safe AI Application Architecture — Integrating Zod Schemas, Structured Output, and Streaming
Type-safe AI applications with the Gemini API and TypeScript: Zod validation, Structured Output, streaming pipelines, and error handling that holds up in production.
Your Gemini API Average Latency Looks Great — But Some Users Still Get Stuck. Defending p95/p99
Your average TTFT is fast, yet a fraction of users keep hitting frozen responses. That is a tail-latency problem (p95/p99). From measurement to model routing, streaming budgets, cache accounting, and retry design — here are the defenses that actually held up in production, with code.
A Lightweight Gemini Backend with Bun and Hono — Reclaiming the Small Tools of Indie Development
Has your Node and Express Gemini backend grown heavy with dependencies and build times? Here is how I moved one to Bun and Hono — folding streaming, rate limiting, cost caps, testing, and self-hosting into a single light runtime — along with the pitfalls I hit in production.
Replaying Gemini API Calls Locally with msw and HTTP Fixtures — How I Cut API Quota Across Six Sites with a Record/Replay Pattern
When you hit the real Gemini API every time you tweak a piece of UI, you end up paying for hundreds of duplicate calls a day. After moving six of my sites to an msw-based record/replay pattern, monthly Gemini billing went unexpectedly quiet. Here's the implementation and operating policy.
Why Gemini API Streaming Drops on iOS After Backgrounding — and How to Fix It
When your iOS app receives a streaming response from Gemini API and the user briefly switches to another app, the stream often goes silent forever. Here's how URLSession actually treats long-lived HTTP, and the smallest change that brings reliability back.
When Gemini API Streaming Cuts Off Mid-Response in Production: The Diagnosis Order I Run
How I diagnose mid-response cutoffs in Gemini API streaming - the order I check network, SDK, and server-side suspects, with real cases from indie production.
Gemini API Streaming Works Locally but Buffers in Production — Fixing Cloud Run, Vercel, and Cloudflare
Streaming responses flow token-by-token in local dev, then arrive as one big blob in production. A walkthrough of the five most common causes — Cloud Run timeouts, Vercel runtime mismatch, Cloudflare Workers proxying, server-side text() pitfalls, and client-side decoding — with the fixes I use across Dolice Labs.