Google CloudSpeech-to-text

gemini-3.5-transcribe-live

JSON

Gemini 3.5 Transcribe Live STT GA streaming, websocket

Live API (WebSocket) streaming variant of Gemini 3.5 Transcribe with automatic language detection and custom vocabulary; 10-minute sessions.

01 Price

$3.50per 1M tokens

Plan or modePrice
text_output$21.00 per 1M tokens

Gemini Developer API paid tier: audio input $3.50 per 1M tokens (~$0.005/min), text output $21.00 per 1M tokens (~$0.004/min).

Pricing source, checked 2026-11-18

02 Languages 77, 83 with regional variants

Show all 77 languages

03 Features 2 of 11 listed

  • Word timestampsnot listed
  • Speaker diarizationnot listed
  • Punctuationnot listed
  • Profanity filternot listed
  • Custom vocabulary
  • Language detection
  • Translationnot listed
  • Sentimentnot listed
  • PII redactionnot listed
  • Summarizationnot listed
  • Topic detectionnot listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Get this record

curl https://voicedex.dev/v1/providers/google-cloud/models/gemini-3.5-transcribe-live

Free, no key needed. Use model id gemini-3.5-transcribe-live with Google Cloud's own API. API reference.

Esc

↑↓ move↵ open