Gemini 3.5 Transcribe: Pricing, Performance & Examples
Gemini 3.5 Transcribe is a speech-to-text model from Google, released in August 2026, with pricing from $2.00/M input and $12.00/M output.
Google Gemini 3.5 Transcribe (`gemini-3.5-transcribe`) is a speech-to-text model for pre-recorded / file audio via the Interactions and generateContent APIs (unary, non-streaming). It supports 85+ languages, smart transcription, and custom
Gemini 3.5 Transcribe benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Quality Tracker
Gemini 3.5 Transcribe Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Sep 05 2026Gemini 3.5 Transcribe pricing
Providers
Gemini 3.5 Transcribe starts at $2.00 per million input tokens and $12.00 per million output tokens via Google.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Google | $2.00 | — | $12.00 | —/— | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Gemini 3.5 Transcribe API
Any audio format up to 25 MB.
Run a request to see the response
Use it in your code
OpenAI-compatible endpoint through the LLM Stats gateway.
import requests
with open("audio.mp3", "rb") as f:
response = requests.post(
"https://gateway.llm-stats.com/v1/stt/transcribe",
headers={"Authorization": "Bearer YOUR_API_KEY"},
files={"file": f},
data={"model_id": "gemini-3.5-transcribe"},
)
print(response.json()["text"])Need an API key? Create one above in the playground, or read the API documentation.
Gemini 3.5 Transcribe latency
Gemini 3.5 Transcribe time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Gemini 3.5 Transcribe license
Gemini 3.5 Transcribe is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
Gemini 3.5 Transcribe resources
Official sources for Gemini 3.5 Transcribe: api documentation, official playground, official launch post.
Gemini 3.5 Transcribe vs other models
The most-compared alternatives to Gemini 3.5 Transcribe are Qwen2.5-Omni-7B, Gemini 1.0 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Gemini 3.5 Transcribe
Models ranked just above and below Gemini 3.5 Transcribe by LLM Stats score.
FAQ
Common questions about Gemini 3.5 Transcribe.