Press "Enter" to skip to content

Posts published by “Abiel Abuy”

Google Launches Gemini 3.5 Transcribe for Precise Multilingual Speech-to-Text

August 27, 2026
Google Launches Gemini 3.5 Transcribe for Precise Multilingual Speech-to-Text

From blog.google;

Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions. Unlike conventional speech recognition models that struggle with background noise, complex jargon, and disfluency cleanup, Gemini 3.5 Transcribe converts raw audio directly into accurate, polished, formatted text.

Key Technical Capabilities

  • Automated Code-Switching & Language Detection: Supports over 85 languages and regional locales automatically. It dynamically handles sentence-level and intra-sentence language switching (code-mixing) without requiring pre-configured language hints.
  • Smart Transcription & Disfluency Removal: Automatically strips out filler words (e.g., “um,” “ah”), cleans up mid-sentence self-corrections, and normalizes spoken text into structured formats—converting phrases like “twenty five dollars” directly into “$25”.
  • Custom Vocabulary Biasing: Developers can supply up to 1,000 custom terms, acronyms, or domain-specific jargon phrases to ensure accurate recognition of specialized names and terminology.
  • Speed & Accuracy Benchmarks: Delivers a 70% faster time-to-final-transcription compared to Chirp 3. According to Artificial Analysis measurements, it achieves a 2.6% Word Error Rate (WER) on non-streaming tasks and a 4.0% WER in streaming mode.
  • Speaker Diarization & Word-Level Timestamps: Attributes speech segments for up to 8 distinct speakers and generates start and end time offsets down to the individual word for precise media indexing.

Dual Integration Paths

Feature / Model gemini-3.5-transcribe (Interactions API) gemini-3.5-transcribe-live (Live API)
Primary Use Case Recorded audio files, meeting logs, interviews Sub-second real-time streaming, voice agents
Max Audio Length Up to 1 hour (30 min with timestamps/diarization) 10 minutes per active session
Word-Level Timestamps Supported Not Supported
Speaker Diarization Supported (Up to 8 speakers) Not Supported

Consumer & Ecosystem Availability

In addition to developer access via Google AI Studio and Google Antigravity, Google is integrating Gemini 3.5 Transcribe across its wider product ecosystem:

  • Android (Gboard Rambler): Powers “Rambler,” converting long-form spoken thoughts into formatted notes and allowing voice-driven style updates.
  • Desktop & Browsers: Drives voice interaction in the Gemini macOS app, integrates screen context via Antigravity to increase spelling accuracy, and will soon enable direct voice-to-text dictation across Chrome web fields.

Welcome to “the boring bot!”

August 27, 2026
Welcome to “the boring bot!”

There is an overwhelming amount of noise surrounding Artificial Intelligence right now. Every single day brings another wave of breathless headlines, fear-mongering sci-fi predictions, and revolutionary breakthroughs that often turn out to be nothing more than impressive demo videos.

That is exactly why I built “The Boring Bot.”

I wanted to create a dedicated space to strip away the sensationalism and document what actually matters: real learnings, hands-on resources, and straightforward news across the entire AI ecosystem.

Here, “boring” is a badge of honor. It means we focus on utility, stability, implementation, and factual intelligence over internet drama.

What You Can Expect Here
Whether you are a developer building production-ready apps, an IT leader evaluating cloud infrastructure, or simply an enthusiast trying to make sense of the rapid pace of change, this platform is set up to cover AI from every practical angle:

  • Hardware & Compute: Unpacking the silicon powering the shift—from enterprise data center GPUs and custom ASICs to local workstation chips, edge runtimes, and local inference specs.
  • Software & Frameworks: Hands-on notes, model benchmarks, open-source libraries, developer APIs, and agentic workflows that you can actually deploy today.
  • Cloud & Infrastructure: Straightforward breakdowns of model hosting, vector databases, server monitoring, and scaling pipelines without hidden cost traps.
  • The Companies & Market: No-BS updates on the major players, emerging startups, open-source maintainers, regulation policies, and industry shifts that impact real-world tech stack decisions.
  • Curated Training & Resources: A growing hub of practical documentation, implementation guides, and tutorials to help you sharpen your technical skills.

A Quick Mandatory Disclosure:

Let’s be honest—it wouldn’t truly be a site about AI if I didn’t actually use AI to help draft, structure, and polish the articles here. Rest assured, human hands are at the steering wheel, but the bots are definitely doing the heavy lifting in the engine room. Think of it as drinking our own Kool-Aid, purely in the name of efficiency.

My Goal
This site exists to serve as a reliable, noise-free notebook and news hub. If a piece of tech is useful, efficient, and solves a real problem, you will read about it here—without the hype.

Thank you for dropping in for post number one. Bookmark the page, subscribe to updates, and let’s get down to the practical work of building with AI.