Google DeepMind launched Gemini 3.5 Transcribe, its most precise speech-to-text model for intelligent voice interactions. Artificial Analysis reports 4.0% streaming WER and 2.6% non-streaming WER, with 85+ languages and screen-aware dictation in Antigravity that grounds filenames, variables, and agent thoughts.

Key Takeaways

  • ✓4.0% streaming WER and 2.6% non-streaming WER; ~70% faster time-to-final-transcription vs Chirp 3, with 5.50% FLEURS streaming WER
  • ✓Live API model gemini-3.5-transcribe-live for sub-second bidirectional streaming; Interactions API gemini-3.5-transcribe adds speaker attribution and word-level timestamps
  • ✓Live in Google AI Studio, Antigravity with screen/chat grounding, Gemini on macOS, and Gboard Rambler; custom vocabulary plus auto-detect for 85+ languages
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
4.0% streaming WER and 2.6% non-streaming WER; ~70% faster time-to-final-transcription vs Chirp 3, with 5.50% FLEURS streaming WER
Full Leaderboard→
💰 Cost & PlansCompare
Gemini 3.5 Flash · in: $1.5 / out: $9
Compare Plans↗
🛠️ Ecosystem & IDERules
Google Antigravity (AGY)
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextGemini API Deprecates Gemini 2.5 Pro and 2.5 Flash: From December 1, Requests Auto-Route to 3.8 Flash and 3.5 Flash-Lite at the New Models' Rates
Read Now→