# GPT Transcribe

> Run GPT Transcribe by openai online or via API. $0.0045/min of audio for files, $0.017/min for realtime, no setup.

**URL:** https://inference.sh/apps/openai/gpt-transcribe
**Last updated:** 2026-11-11

---

Transcribe speech with OpenAI. Send a recording and get its transcript from GPT Transcribe, or stream a microphone over a socket and read the transcript as it is spoken with GPT Live Transcribe.

- app: `openai/gpt-transcribe`
- maker: [openai](https://inference.sh/apps/openai.md)
- category: [audio](https://inference.sh/apps/category/audio.md)
- input → output: speech → text
- tasks: [speech to text](https://inference.sh/apps/tag/speech-to-text.md), [realtime](https://inference.sh/apps/tag/realtime.md)
- price: $0.0045/min of audio for files, $0.017/min for realtime
- runs via: api, javascript and python sdk, belt cli, mcp

## gpt-transcribe API Guide

### About
transcribe speech with openai. send a recording and get its transcript from gpt transcribe, or stream a microphone over a socket and read the transcript as it is spoken with gpt live transcribe.

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @0rk3f62m pinned
result = client.run({
        "app": "openai/gpt-transcribe@0rk3f62m",
        "input": {
            "audio": "https://example.com/file.png"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @0rk3f62m pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "openai/gpt-transcribe@0rk3f62m",
        "input": {
            "audio": "https://example.com/file.png"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "openai/gpt-transcribe@0rk3f62m",
        "input": {
            "audio": "https://example.com/file.png"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "openai/gpt-transcribe@0rk3f62m",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **audio** (string) *required*: The recording: mp3, mp4, mpeg, mpga, m4a, wav, webm, flac or ogg, up to 25 MB
- **prompt** (string): What the recording is, or where it was made: context that helps with what is said in it
- **languages** (array): The languages expected, as ISO 639-1 codes such as en or fr. Left empty the language is detected.
- **keyterms** (array): Product names, acronyms and other literal terms that may be said. Each on one line, without < or >.

#### Output
- **duration** (number): Length of the audio, in seconds
- **languages** (array): The languages OpenAI detected; empty when it could not tell
- **text** (string): The transcript

## other audio apps

- [Pika H3 Flex Audio Stems](https://inference.sh/apps/pika/pika-h3-flex-audio-stems.md): $0.001/stem-sec (3 stems: dialogue, music, effect)
- [Fish Audio Drama 3](https://inference.sh/apps/fish-audio/drama-3.md): $50.00/1M UTF-8 bytes
- [Eleven Flash v2.5](https://inference.sh/apps/elevenlabs/eleven-flash-v2-5.md): $0.04/1K characters
- [Eleven Multilingual v2](https://inference.sh/apps/elevenlabs/eleven-multilingual-v2.md): $0.08/1K characters
- [Eleven v3](https://inference.sh/apps/elevenlabs/eleven-v3.md): $0.08/1K characters

## faq

### how much does GPT Transcribe cost?

$0.0045/min of audio for files, $0.017/min for realtime. you pay per run from your inference shell credits. no subscription is required.

### how do I run GPT Transcribe via api?

call openai/gpt-transcribe with the javascript or python sdk, the rest api, or `belt app run openai/gpt-transcribe` from a terminal. the api reference on this page lists every input.

### who makes GPT Transcribe?

GPT Transcribe is made by openai and runs on inference shell. every openai app is listed at https://inference.sh/apps/openai.

### can my agent use GPT Transcribe?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to GPT Transcribe?

other audio apps on inference shell include Pika H3 Flex Audio Stems, Fish Audio Drama 3, Eleven Flash v2.5, Eleven Multilingual v2. they run through the same api, so switching is a one-line change.
