Models

GPT Transcribe

Model id: gpt-transcribe

  • Audio

OpenAI’s current file speech-to-text model.

Best for

recorded audio when you need the words.

Provider
OpenAI
Context window
Not published
Release date
2026-07-28

Pricing

Input
$0.0001 / s

Amounts in Canadian dollars, converted at the Bank of Canada indicative rate (2026-09-21).

Performance

Reading

Last 7 days

Not enough data to display the chart.

Time to first byte (p95)
Not published
Output speed (p95)
Not published
Samples
1 over 7 days

Measured on real traffic at Pass egress — not a synthetic benchmark.

Activity

Tokens

Top 5 tools · last 7 days

Tool activity appears only when at least 2 workspaces have used this model recently.

Availability

Availability (%)

Last 7 days

Operational probes
99.98% over 7 days
Samples
9,210

View service status

Quick start

Transcribe an audio file with a tonia_ key and the exact model id below.

curl

curl https://pass.tonia.ca:8443/v1/audio/transcriptions \
  -H "Authorization: Bearer $TONIA_API_KEY" \
  -F "model=gpt-transcribe" \
  -F "file=@clip.wav"

Python (tonia SDK)

import os
from tonia import Tonia

client = Tonia(api_key=os.environ["TONIA_API_KEY"])
with open("clip.wav", "rb") as audio:
    transcript = client.audio.transcriptions.create(
        model="gpt-transcribe",
        file=audio,
        filename="clip.wav",
    )

TypeScript (tonia SDK)

import { Tonia } from "@tonia-router/sdk";

const client = new Tonia({
  apiKey: process.env.TONIA_API_KEY,
});

const transcript = await client.audio.transcriptions.create({
  model: "gpt-transcribe",
  file: new Blob(),
  filename: "clip.wav",
});

Create a key in the portal