Google said on X that it is bringing Gemini 3.5 Transcribe's voice editing, the same technology behind Rambler on Gboard and the Gemini app on macOS, to the Gemini API. The official changelog shows gemini-3.5-transcribe and gemini-3.5-transcribe-live gained voice-driven editing, rewriting and formatting on November 17. It is on by default in Smart transcription mode: users can dictate and give spoken edit instructions in the same recording, or pass up to 64 KiB of existing text in source_text, and the model applies the instructions and returns the complete updated text.

Key Takeaways

  • ✓gemini-3.5-transcribe and gemini-3.5-transcribe-live in the Gemini API gained voice editing on November 17; Google promoted it on X on November 20
  • ✓It is on by default when transcription_config mode is smart, so dictation and spoken edit instructions can be in the same recording
  • ✓Pass up to 64 KiB of existing text in source_text and the model edits, rewrites or formats it from spoken instructions, returning the complete updated text in output_text
  • ✓In Live API sessions the server keeps the active text and emits the full replacement in input_transcription; interim_input_transcription only streams the literal instruction, so wait for the final result before updating a document
  • ✓Paid-tier pricing is $2.00 per 1M audio input tokens and $12.00 per 1M text output tokens, an estimated blended ~$0.005 per minute; no voice-editing benchmarks were published
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
No model benchmark in this story · see current rankings
Full Leaderboard→
🛠️ Ecosystem & IDERules
Gemini API · Speech-to-text · Voice editing
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

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

🔬

In-Depth Technical Analysis

Background

Voice input usually stops at verbatim transcription, so fixing a sentence still means going back to the keyboard. Google already uses voice editing in Rambler on Gboard and the Gemini app on macOS, and announced on X that it is now available in the Gemini API; the changelog shows it shipped on November 17.

How it works

Per the transcription docs, voice editing is on by default in Smart mode. One recording can contain both dictation and instructions such as rewrite or format, or you can pass up to 64 KiB of existing text in source_text and get the complete updated text back. In Live transcription the server keeps the active text for the session and emits the full replacement each time.

Numbers that matter

Google published no voice-editing benchmarks. The pricing page lists $2.00 per 1M audio input tokens and $12.00 per 1M text output tokens on the paid tier, an estimated blended ~$0.005 per minute, with a free tier available.

What it means for developers

Call gemini-3.5-transcribe through the Interactions API with mode set to smart and optional source_text; for real time use the Live API and wait for the final input_transcription before writing to your document. Good fits are voice notes, email rewriting and hands-free editors.

Action HubReady to adopt this in production?

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

Up NextArtificial Analysis Launches the Diarization Index for Speech to Text: APIs Scored on Word Diarization Error Rate, NVIDIA Nemotron 3.5 Transcribe Leads at 3.3% Ahead of Voxtral Small Transcribe 3 at 7.5%
Read Now→