google
Gemini 3.5 Transcribe
Transcription by google
audiotext
Overview
- Type
- transcription
- Context
- —
- Max output
- —
- Input / output
- audio / text
API
Model identifier
google/gemini-3.5-transcribeProviders and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Operational | — | — | 100.00% / 100.00% / 99.95% | $2.00/M | $12.00/M | — / — | — | — | — | Yes |
Pricing
input
0.000002
output
0.000012
audio input token cost
0.000002
Capabilities
audiotext
Supported parameters
No details published for this model.
Reasoning options
options
{
"type": "effort",
"values": [
"low",
"high"
]
}
Metadata
type
transcription
context window
—
max output
—
released
Aug 26, 2026
zero data retention
none
no training
all
api specifications
v2, v3, v4