Skip to content
FluxCDNFluxCDN
esc

Google: Gemini 3.5 Transcribe

Speech to text

Gemini 3.5 Transcribe is a speech-to-text model from Google. It is suited for synchronous transcription that needs word-level timestamps or speaker diarization, with support for up to eight speakers.

Price
720,776 Toman/M in · 4,324,656 Toman/M out
Endpoint
POST /v1/audio/transcriptions
Published
Sep 25, 2026
Offers
With segment and word times
Maker
Google

Free plan prices, in Toman at today's rate. Plans and prices

Price on each plan

Per millisecond of audio heard, shown a minute at a time, in Toman at today's rate; never below what the provider charges us plus your plan's margin.

PlanPrice
Free720,776 Toman/M in · 4,324,656 Toman/M out
Pro691,236 Toman/M in · 4,147,416 Toman/M out
Max661,696 Toman/M in · 3,970,176 Toman/M out

Call it

curl https://ai.fluxcdn.cloud/api/v1/audio/transcriptions -H "Authorization: Bearer $FLUXCDN_API_KEY" \
  -F file=@voice.mp3 -F model=google/gemini-3.5-transcribe -F language=fa \
  -F response_format=srt