Google: Gemini 3.5 Transcribe
Speech to textGemini 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
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.
| Plan | Price |
|---|---|
| Free | 720,776 Toman/M in · 4,324,656 Toman/M out |
| Pro | 691,236 Toman/M in · 4,147,416 Toman/M out |
| Max | 661,696 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
