Google Launches Gemini 3.5 Transcribe Speech-to-Text Model

On Aug 27, Google launched Gemini 3.5 Transcribe, announced by Sundar Pichai on X. The speech-to-text model emphasizes high-accuracy transcription with smart post-processing, shipping in both pre-recorded and real-time streaming (Live) versions, with APIs live on Google AI Studio and Gemini Enterprise and integrated across Google products. Third-party benchmarks are strong though not top-ranked, and community reception is largely positive, with some puzzled by function calling in a transcription model.

Confirmed

• Supports 85+ languages and regional accent auto-detection, real-time streaming and batch processing, lower WER, sub-second latency, and mixed-language input (e.g., Chinese-English)
• Speaker identification, speaker diarization, word-level timestamps, and custom vocabulary for jargon and specialized terms
• Smart post-processing: filters filler words, intent-based rewriting and formatting; per @stefanjblos's relayed test, offers both verbatim and SMART modes
• Enhanced understanding of phone numbers, postal codes, and order IDs, robust in noisy environments
• Function calling: with permission, combines screen context and chat history (e.g., filenames, agent reasoning) to execute voice commands, designed for voice interaction in Google Antigravity
• Two variants: standard for recorded audio (with diarization and word timestamps), Live for real-time voice applications
• Per Artificial Analysis: non-streaming AA-WER of 2.6% (rank 5), 84x real-time speed, 0.4s latency; Live reaches 5.8% accuracy 0.25s after end-of-speech detection, faster first response than GPT Live
• @philschmid's tests: non-streaming WER 2.6%, streaming WER 4.0%, 70% faster final transcription vs Chirp 3, with excellent post-processing
• @GoogleAI's weekly roundup highlighted the model alongside Gemini Omni 1.1 Flash

Unconfirmed

• @giffmana questioned why a transcription model needs Function Calling; the official design rationale remains unexplained
• Rank 5 on AA-WER implies a gap to leading models; full leaderboard details were not provided

Why it matters

• Background noise, filler words, and misspellings are long-standing dictation pain points the model directly targets
• Speaker diarization, custom vocabulary, and function calling make it embeddable in real-time voice apps and enterprise workflows
• Developers including @thorwebdom and @philschmid have posted demos and positive hands-on results, signaling real-world potential in professional scenarios

2026-08-27 ~ 2026-08-28 · 29 related posts

Full story(2 episodes)→

• Episode 1: Google Launches Gemini 3.5 Transcribe Speech-to-Text Model(2026-08-27, 29 posts)
• Episode 2: Developer Open-Sources Dictation App Built on Gemini 3.5 Transcribe(2026-08-27, 2 posts)

• Google DeepMind releases Gemini 3.5 Transcribe for precise speech-to-text — GoogleDeepMind · 2026-08-27
• Google releases Gemini 3.5 Transcribe with smart post-processing — GoogleDeepMind · 2026-08-27
• [source] Hands-on: Gemini 3.5 Transcribe achieves 2.6% WER, excellent post-processing — _philschmid · 2026-08-27
• Demis Hassabis retweets: Gemini 3.5 Transcribe launch, multi-speaker support — demishassabis · 2026-08-27
• [source] Google launches Gemini 3.5 Transcribe: 85+ languages, auto-filters filler words — GoogleAI · 2026-08-27
• Google launches Gemini 3.5 Transcribe for precise, noise-canceling dictation — GoogleAI · 2026-08-27
• Google launches two Gemini 3.5 Transcribe models for offline and live use — patloeber · 2026-08-27
• Demo shows Gemini 3.5 Transcribe features smart rewrite and custom vocabulary — patloeber · 2026-08-27
• Google introduces Gemini 3.5 Transcribe on its official blog — patloeber · 2026-08-27
• Google releases Gemini 3.5 Transcribe: filters filler words and understands codebase context — AI_Andrew · 2026-08-27
• Gemini 3.5 Transcribe launches to strong reception — Saboo_Shubham_ · 2026-08-27
• Gemini 3.5 Transcribe launches; Enterprise Agent Platform enters public preview — Saboo_Shubham_ · 2026-08-27
• Gemini 3.5 Transcribe launches with 85+ languages and function calling — osanseviero · 2026-08-27
• Gemini 3.5 Transcribe Released: Why Function Calling in a Speech-to-Text Model? — giffmana · 2026-08-27
• Google launches Gemini 3.5 Transcribe with context-aware precision for voice interactions — rseroter · 2026-08-27
• Hands-on: Gemini Transcribe 3.5 offers verbatim and smart modes — stefanjblos · 2026-08-27
• [source] Google launches Gemini 3.5 Transcribe with 2.6% WER and 0.4s latency — ArtificialAnlys · 2026-08-27
• Gemini 3.5 Transcribe Live Beats GPT Live Transcribe: 5.8% WER at 0.25s First Partial — ArtificialAnlys · 2026-08-27
• Gemini 3.5 Transcribe Live pricing higher than competitors at $9/1k mins — ArtificialAnlys · 2026-08-27
• Gemini 3.5 Transcribe Live costs ~$9/1k minutes, pricier than Cartesia and Deepgram — ArtificialAnlys · 2026-08-27
• Google's week: Gemini 3.5 Transcribe, Omni 1.1 Flash, Live upgrades and more — GoogleAI · 2026-08-28

8 near-duplicate retellings: OfficialLoganK · ammaar · osanseviero · ArtificialAnlys · ocean_protocol · vista8 · vista8 · jocarrasqueira