---
type: AI Model
id: gpt-4o
title: OpenAI Text to Speech API
provider: OpenAI
description: "OpenAI's GPT-4o audio models on one API. For text to speech, GPT-4o Mini is the low-latency option and GPT-4o Mini HD trades speed for cleaner audio at twice the price — six voices and six output containers on both, with speed control from a quarter to four times normal. In the other direction, GPT-4o Transcribe converts speech to text with high accuracy."
resource: https://www.pixazo.ai/models/gpt-4o
docs_url: https://www.pixazo.ai/models/gpt-4o
latest_version: GPT-4o Mini
tags:
  - text-to-speech
  - speech-to-text
  - openai
variants:
  - id: tts-1
    name: GPT-4o Mini TTS
    version: GPT-4o Mini
    capabilities:
      - Text to Speech
  - id: tts-1-hd
    name: GPT-4o Mini TTS HD
    version: GPT-4o Mini HD
    capabilities:
      - Text to Speech
  - id: gpt-4o-transcribe
    name: GPT-4o Transcribe
    version: GPT-4o
    capabilities:
      - Speech to Text
timestamp: 2026-08-24T04:16:36.558Z
---

# OpenAI Text to Speech API

> Provider: **OpenAI**
> Source: https://www.pixazo.ai/models/gpt-4o

OpenAI's GPT-4o audio models on one API. For text to speech, GPT-4o Mini is the low-latency option and GPT-4o Mini HD trades speed for cleaner audio at twice the price — six voices and six output containers on both, with speed control from a quarter to four times normal. In the other direction, GPT-4o Transcribe converts speech to text with high accuracy.

## GPT-4o Mini TTS

### Text to Speech

## OpenAI TTS 1 API Documentation

OpenAI's low-latency voice model. Six voices, six output containers, and speed control from a quarter to four times normal. Asynchronous: submit returns a `request_id`; poll the status endpoint until the request is `COMPLETED`, then download the audio.

```
POST https://gateway.pixazo.ai/tts-1/v1/text-to-speech
```

## Authentication

All requests require an API key passed via header.

Header

Type

Required

Description

Ocp-Apim-Subscription-Key

string

Yes

Your API subscription key

## Text to Speech - OpenAI TTS 1

## Request Code

HTTP Python JavaScript cURL

```
POST https://gateway.pixazo.ai/tts-1/v1/text-to-speech
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "text": "Hello from Pixazo. This is a text to speech demo."
}
```

```
import requests

url = "https://gateway.pixazo.ai/tts-1/v1/text-to-speech"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "text": "Hello from Pixazo. This is a text to speech demo."
}

resp = requests.post(url, json=data, headers=headers)
print(resp.json())
```

```
const res = await fetch("https://gateway.pixazo.ai/tts-1/v1/text-to-speech", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "text": "Hello from Pixazo. This is a text to speech demo."
})
});
console.log(await res.json());
```

```
curl -X POST 'https://gateway.pixazo.ai/tts-1/v1/text-to-speech' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"text": "Hello from Pixazo. This is a text to speech demo."}'
```

## Output

```
{
  "request_id": "tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

[Try Now](https://api.pixazo.ai/api-details#api=tts-1&operation=text-to-speech)

## Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state. Provide a Webhook URL via header on the submit request.

Header

Required

Description

X-Webhook-URL

To enable

HTTPS URL to receive the Webhook callback.

X-Webhook-Mode

No

`terminal` (default, one callback on COMPLETED/ERROR) or `sync` (per-poll callbacks).

### Example: enable Webhook

```
curl -X POST 'https://gateway.pixazo.ai/tts-1/v1/text-to-speech' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"text": "Hello from Pixazo. This is a text to speech demo."}'
```

### Callback Payload (success)

```
{
  "request_id": "tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "tts-1",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp3"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-08-01T09:14:16.102Z",
  "completed_at": "2026-08-01T09:14:22.870Z"
}
```

### Failure callback shape

```
{
  "request_id": "tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "tts-1",
  "error": "Description of the failure"
}
```

#### Delivery semantics

-   **terminal** mode: one Webhook callback when the request is COMPLETED or ERROR.
-   **sync** mode: a Webhook callback on each status change.
-   Callbacks are idempotent on `request_id` — de-duplicate on it.
-   Respond `200` within a few seconds; the Webhook endpoint must be HTTPS.

## Request Parameters

Parameter

Required

Type

Default

Allowed values / range

Description

`text`

Yes

string

—

up to 4,096 characters

The text to speak. `input` is accepted as an alias.

`voice`

No

string

`alloy`

`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`

Which OpenAI voice to use.

`response_format`

No

string

`mp3`

`mp3`, `opus`, `aac`, `flac`, `wav`, `pcm`

Output container. The file you receive is stored with the matching extension.

`speed`

No

number

`1`

0.25 – 4

Playback speed multiplier.

### Voices

Six voices: alloy, echo, fable, onyx, nova, shimmer. Up to 4,096 characters per request.

## Example Request

```
{
  "text": "Hello from Pixazo. This is a text to speech demo."
}
```

## Example Response

```
{
  "request_id": "tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

## Request Headers

Header

Required

Description

Content-Type

Yes

`application/json`

Ocp-Apim-Subscription-Key

Yes

Your API subscription key.

X-Webhook-URL

No

Enable Webhook callbacks (see Webhook section).

## Response Handling

Status Code

Meaning

202

Accepted — request queued; returns `request_id` and `polling_url`.

400

Bad request — a missing or out-of-range parameter. The message names the field.

401

Unauthorized — missing or invalid subscription key.

402

Insufficient balance.

429

Too many requests.

500

Internal server error.

## Retrieving Results

Poll the status endpoint with the `request_id` from the submit response until `status` is `COMPLETED` (or `ERROR`), then download `output.media_url`.

```
curl 'https://gateway.pixazo.ai/v2/requests/status/tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'
```

### Completed response

```
{
  "request_id": "tts-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "tts-1",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp3"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-08-01T09:14:16.102Z",
  "completed_at": "2026-08-01T09:14:22.870Z"
}
```

## Response Fields

Field

Type

Description

request\_id

string

Unique request identifier.

status

string

QUEUED, PROCESSING, COMPLETED or ERROR.

model\_id

string

The model that handled the request.

output.media\_url

array

URL of the generated audio file.

output.media\_type

string

MIME type of the audio.

created\_at

string

Request creation timestamp.

completed\_at

string

Completion timestamp.

error

string

Error message when `status` is ERROR.

## Status Values & Flow

`QUEUED` → `PROCESSING` → `COMPLETED` (success) or `ERROR` (failure).

### Pricing

Billed at **$0.015 per 1,000 characters** of input text, rounded up to the next whole 1,000. You are charged for the text you submit, not the length of the audio produced.

Input text

Billed blocks

Cost

A short sentence (~50 characters)

1

$0.015

A paragraph (~800 characters)

1

$0.015

A 3,000-character article

3

$0.045

10,000 characters

10

$0.15

Failed requests are not billed.

## GPT-4o Mini TTS HD

### Text to Speech

## OpenAI TTS 1 HD API Documentation

The high-quality half of OpenAI's text-to-speech pair. Same voices and controls as TTS 1, with cleaner audio, at twice the price. Asynchronous: submit returns a `request_id`; poll the status endpoint until the request is `COMPLETED`, then download the audio.

```
POST https://gateway.pixazo.ai/tts-1-hd/v1/text-to-speech
```

## Authentication

All requests require an API key passed via header.

Header

Type

Required

Description

Ocp-Apim-Subscription-Key

string

Yes

Your API subscription key

## Text to Speech - OpenAI TTS 1 HD

## Request Code

HTTP Python JavaScript cURL

```
POST https://gateway.pixazo.ai/tts-1-hd/v1/text-to-speech
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "text": "Hello from Pixazo. This is a text to speech demo."
}
```

```
import requests

url = "https://gateway.pixazo.ai/tts-1-hd/v1/text-to-speech"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "text": "Hello from Pixazo. This is a text to speech demo."
}

resp = requests.post(url, json=data, headers=headers)
print(resp.json())
```

```
const res = await fetch("https://gateway.pixazo.ai/tts-1-hd/v1/text-to-speech", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "text": "Hello from Pixazo. This is a text to speech demo."
})
});
console.log(await res.json());
```

```
curl -X POST 'https://gateway.pixazo.ai/tts-1-hd/v1/text-to-speech' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"text": "Hello from Pixazo. This is a text to speech demo."}'
```

## Output

```
{
  "request_id": "tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

[Try Now](https://api.pixazo.ai/api-details#api=tts-1-hd&operation=text-to-speech)

## Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state. Provide a Webhook URL via header on the submit request.

Header

Required

Description

X-Webhook-URL

To enable

HTTPS URL to receive the Webhook callback.

X-Webhook-Mode

No

`terminal` (default, one callback on COMPLETED/ERROR) or `sync` (per-poll callbacks).

### Example: enable Webhook

```
curl -X POST 'https://gateway.pixazo.ai/tts-1-hd/v1/text-to-speech' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"text": "Hello from Pixazo. This is a text to speech demo."}'
```

### Callback Payload (success)

```
{
  "request_id": "tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "tts-1-hd",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp3"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-08-01T09:14:16.102Z",
  "completed_at": "2026-08-01T09:14:22.870Z"
}
```

### Failure callback shape

```
{
  "request_id": "tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "tts-1-hd",
  "error": "Description of the failure"
}
```

#### Delivery semantics

-   **terminal** mode: one Webhook callback when the request is COMPLETED or ERROR.
-   **sync** mode: a Webhook callback on each status change.
-   Callbacks are idempotent on `request_id` — de-duplicate on it.
-   Respond `200` within a few seconds; the Webhook endpoint must be HTTPS.

## Request Parameters

Parameter

Required

Type

Default

Allowed values / range

Description

`text`

Yes

string

—

up to 4,096 characters

The text to speak. `input` is accepted as an alias.

`voice`

No

string

`alloy`

`alloy`, `echo`, `fable`, `onyx`, `nova`, `shimmer`

Which OpenAI voice to use.

`response_format`

No

string

`mp3`

`mp3`, `opus`, `aac`, `flac`, `wav`, `pcm`

Output container. The file you receive is stored with the matching extension.

`speed`

No

number

`1`

0.25 – 4

Playback speed multiplier.

### Voices

Six voices: alloy, echo, fable, onyx, nova, shimmer. Up to 4,096 characters per request.

## Example Request

```
{
  "text": "Hello from Pixazo. This is a text to speech demo."
}
```

## Example Response

```
{
  "request_id": "tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

## Request Headers

Header

Required

Description

Content-Type

Yes

`application/json`

Ocp-Apim-Subscription-Key

Yes

Your API subscription key.

X-Webhook-URL

No

Enable Webhook callbacks (see Webhook section).

## Response Handling

Status Code

Meaning

202

Accepted — request queued; returns `request_id` and `polling_url`.

400

Bad request — a missing or out-of-range parameter. The message names the field.

401

Unauthorized — missing or invalid subscription key.

402

Insufficient balance.

429

Too many requests.

500

Internal server error.

## Retrieving Results

Poll the status endpoint with the `request_id` from the submit response until `status` is `COMPLETED` (or `ERROR`), then download `output.media_url`.

```
curl 'https://gateway.pixazo.ai/v2/requests/status/tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'
```

### Completed response

```
{
  "request_id": "tts-1-hd_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "tts-1-hd",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/output.mp3"
    ],
    "media_type": "audio/mpeg"
  },
  "created_at": "2026-08-01T09:14:16.102Z",
  "completed_at": "2026-08-01T09:14:22.870Z"
}
```

## Response Fields

Field

Type

Description

request\_id

string

Unique request identifier.

status

string

QUEUED, PROCESSING, COMPLETED or ERROR.

model\_id

string

The model that handled the request.

output.media\_url

array

URL of the generated audio file.

output.media\_type

string

MIME type of the audio.

created\_at

string

Request creation timestamp.

completed\_at

string

Completion timestamp.

error

string

Error message when `status` is ERROR.

## Status Values & Flow

`QUEUED` → `PROCESSING` → `COMPLETED` (success) or `ERROR` (failure).

### Pricing

Billed at **$0.03 per 1,000 characters** of input text, rounded up to the next whole 1,000. You are charged for the text you submit, not the length of the audio produced.

Input text

Billed blocks

Cost

A short sentence (~50 characters)

1

$0.03

A paragraph (~800 characters)

1

$0.03

A 3,000-character article

3

$0.09

10,000 characters

10

$0.3

Failed requests are not billed.

## GPT-4o Transcribe

### Speech to Text

## GPT-4o Transcribe API Documentation

OpenAI's GPT-4o transcription model, called directly against OpenAI. Accepts recordings up to 25 MB in flac, mp3, mp4, m4a, ogg, wav or webm. Asynchronous: submit returns a `request_id`; poll the status endpoint until the request is `COMPLETED`, then download the audio.

```
POST https://gateway.pixazo.ai/gpt-4o-transcribe/v1/speech-to-text
```

## Authentication

All requests require an API key passed via header.

Header

Type

Required

Description

Ocp-Apim-Subscription-Key

string

Yes

Your API subscription key

## Speech to Text - GPT-4o Transcribe

## Request Code

HTTP Python JavaScript cURL

```
POST https://gateway.pixazo.ai/gpt-4o-transcribe/v1/speech-to-text
Content-Type: application/json
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/speech-17s.mp3"
}
```

```
import requests

url = "https://gateway.pixazo.ai/gpt-4o-transcribe/v1/speech-to-text"
headers = {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/speech-17s.mp3"
}

resp = requests.post(url, json=data, headers=headers)
print(resp.json())
```

```
const res = await fetch("https://gateway.pixazo.ai/gpt-4o-transcribe/v1/speech-to-text", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
  },
  body: JSON.stringify({
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/speech-17s.mp3"
})
});
console.log(await res.json());
```

```
curl -X POST 'https://gateway.pixazo.ai/gpt-4o-transcribe/v1/speech-to-text' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  --data-raw '{"audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/speech-17s.mp3"}'
```

## Output

```
{
  "request_id": "gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

[Try Now](https://api.pixazo.ai/api-details#api=gpt-4o-transcribe&operation=speech-to-text)

## Webhook (Optional)

Instead of polling, you can receive a Webhook callback when the request reaches a terminal state. Provide a Webhook URL via header on the submit request.

Header

Required

Description

X-Webhook-URL

To enable

HTTPS URL to receive the Webhook callback.

X-Webhook-Mode

No

`terminal` (default, one callback on COMPLETED/ERROR) or `sync` (per-poll callbacks).

### Example: enable Webhook

```
curl -X POST 'https://gateway.pixazo.ai/gpt-4o-transcribe/v1/speech-to-text' \
  -H 'Content-Type: application/json' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY' \
  -H 'X-Webhook-URL: https://your-server.com/webhook' \
  --data-raw '{"audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/speech-17s.mp3"}'
```

### Callback Payload (success)

```
{
  "request_id": "gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-4o-transcribe",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/transcript.json"
    ],
    "media_type": "application/json"
  },
  "duration": 19.17,
  "created_at": "2026-08-01T09:14:16.102Z",
  "completed_at": "2026-08-01T09:14:22.870Z"
}
```

### Failure callback shape

```
{
  "request_id": "gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "gpt-4o-transcribe",
  "error": "Description of the failure"
}
```

#### Delivery semantics

-   **terminal** mode: one Webhook callback when the request is COMPLETED or ERROR.
-   **sync** mode: a Webhook callback on each status change.
-   Callbacks are idempotent on `request_id` — de-duplicate on it.
-   Respond `200` within a few seconds; the Webhook endpoint must be HTTPS.

## Request Parameters

Parameter

Required

Type

Default

Allowed values / range

Description

`audio_url`

Yes

string

—

a publicly reachable http(s) url

The recording to transcribe. We fetch it server-side, so it must be reachable from the internet — a signed url is fine, a private one is not. `audio` is accepted as an alias.

`language`

No

string

—

ISO 639-1, e.g. `en`

Omit this to let the model detect the language — that is the default. `auto` means the same. Set it to force one of the recording.

`prompt`

No

string

—

up to 2,000 characters

Bias the transcription toward expected wording — names, jargon, spellings.

### Voices

Optional `prompt` biases the transcription toward expected wording; `temperature` accepts 0–1.

## Example Request

```
{
  "audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/doc-assets/audio/speech-17s.mp3"
}
```

## Example Response

```
{
  "request_id": "gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}
```

## Request Headers

Header

Required

Description

Content-Type

Yes

`application/json`

Ocp-Apim-Subscription-Key

Yes

Your API subscription key.

X-Webhook-URL

No

Enable Webhook callbacks (see Webhook section).

## Response Handling

Status Code

Meaning

202

Accepted — request queued; returns `request_id` and `polling_url`.

400

Bad request — a missing or out-of-range parameter. The message names the field.

401

Unauthorized — missing or invalid subscription key.

402

Insufficient balance.

429

Too many requests.

500

Internal server error.

## Retrieving Results

Poll the status endpoint with the `request_id` from the submit response until `status` is `COMPLETED` (or `ERROR`), then download `output.media_url`.

```
curl 'https://gateway.pixazo.ai/v2/requests/status/gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'
```

### Completed response

```
{
  "request_id": "gpt-4o-transcribe_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "gpt-4o-transcribe",
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/{request_id}/transcript.json"
    ],
    "media_type": "application/json"
  },
  "duration": 19.17,
  "created_at": "2026-08-01T09:14:16.102Z",
  "completed_at": "2026-08-01T09:14:22.870Z"
}
```

## Response Fields

Field

Type

Description

request\_id

string

Unique request identifier.

status

string

QUEUED, PROCESSING, COMPLETED or ERROR.

model\_id

string

The model that handled the request.

output.media\_url

array

URL of the generated audio file.

output.media\_type

string

MIME type of the audio.

created\_at

string

Request creation timestamp.

completed\_at

string

Completion timestamp.

error

string

Error message when `status` is ERROR.

## Status Values & Flow

`QUEUED` → `PROCESSING` → `COMPLETED` (success) or `ERROR` (failure).

### Pricing

Billed at **$0.006 per minute of generated audio**, rounded up to the next whole minute. You are charged for the audio produced, not the text you submit.

Audio produced

Billed minutes

Cost

A 10-second clip

1

$0.006

A 45-second clip

1

$0.006

A 3-minute narration

3

$0.018

A 10-minute narration

10

$0.06

Failed requests are not billed.