Pixazo API→Models→Speech to Text API→OpenAI Speech to Text

Whisper Large v3 Turbo API, Whisper Tiny English API, Whisper API: Pricing, Documentation

Whisper Large v3 Turbo API represents a significant leap forward in automated speech recognition, transforming spoken audio into highly accurate text across a multitude of languages and complex acoustic environments. By leveraging state-of-the-art neural networks trained on vast, diverse datasets, it excels at deciphering nuanced accents, filtering out disruptive background noise, and accurately capturing technical jargon. This powerful interface allows developers to seamlessly embed robust voice-to-text capabilities into applications, facilitating real-time transcription, automated subtitling, and deep semantic analysis of spoken content.

Get API Key

Models Version

WELCOME BONUS

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

Whisper Large v3 Turbo API Documentation

OpenAI Whisper Large v3 Turbo, the fastest of the large Whisper models. Returns the transcript plus per-segment timings, word counts and a ready-made WebVTT subtitle track. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/whisper-large-v3-turbo/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 - Whisper Large v3 Turbo

Request Code

POST https://gateway.pixazo.ai/whisper-large-v3-turbo/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/whisper-large-v3-turbo/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/whisper-large-v3-turbo/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/whisper-large-v3-turbo/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": "whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

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/whisper-large-v3-turbo/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": "whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "whisper-large-v3-turbo",
  "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": "whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "whisper-large-v3-turbo",
  "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.
`task`	No	string	`transcribe`	`transcribe`, `translate`	`transcribe` keeps the spoken language; `translate` renders English regardless of the source.
`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. Detection is reported back as `transcription_info.language` with a confidence.
`vad_filter`	No	boolean	`false`	`true`, `false`	Drop silence before transcribing. Useful on long recordings with gaps.
`initial_prompt`	No	string	—	up to 2,000 characters	Bias the model toward expected wording — names, jargon, spellings.

Voices

Transcribes 99 languages and can translate any of them into English in the same call.

Example Request

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

Example Response

{
  "request_id": "whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/whisper-large-v3-turbo_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/whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "whisper-large-v3-turbo_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "whisper-large-v3-turbo",
  "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 $0.00051 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	$0.00051
A 45-second clip	1	$0.00051
A 3-minute narration	3	$0.00153
A 10-minute narration	10	$0.0051

Failed requests are not billed.

Whisper Large v3 Turbo API Pricing

Your request will cost $0.0005 per minute of audio transcribed.

a 3-minute recording is $0.00153; an hour is about $0.03

equivalent to $0.0306 per hour of audio

2. Whisper Tiny English

Whisper Tiny English API Documentation

The smallest Whisper model, English only. Noticeably faster and cheaper than the large models, at some cost in accuracy on proper nouns — a good fit for bulk transcription where a rough transcript is enough. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/whisper-tiny-en/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 - Whisper Tiny English

Request Code

POST https://gateway.pixazo.ai/whisper-tiny-en/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/whisper-tiny-en/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/whisper-tiny-en/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/whisper-tiny-en/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": "whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

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/whisper-tiny-en/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": "whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "whisper-tiny-en",
  "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": "whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "whisper-tiny-en",
  "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.
`task`	No	string	`transcribe`	`transcribe`, `translate`	`transcribe` keeps the spoken language; `translate` renders English regardless of the source.
`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. Detection is reported back as `transcription_info.language` with a confidence.
`vad_filter`	No	boolean	`false`	`true`, `false`	Drop silence before transcribing. Useful on long recordings with gaps.
`initial_prompt`	No	string	—	up to 2,000 characters	Bias the model toward expected wording — names, jargon, spellings.

Voices

English only. language and task=translate have no effect on this model.

Example Request

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

Example Response

{
  "request_id": "whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/whisper-tiny-en_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/whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "whisper-tiny-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "whisper-tiny-en",
  "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 $0.0005 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	$0.0005
A 45-second clip	1	$0.0005
A 3-minute narration	3	$0.0015
A 10-minute narration	10	$0.005

Failed requests are not billed.

Whisper Tiny English API Pricing

Your request will cost $0.0005 per minute of audio transcribed.

an hour of audio is about three cents

equivalent to $0.03 per hour of audio

3. Whisper

Whisper API Documentation

The original OpenAI Whisper model. Transcribes 99 languages and can translate any of them into English, returning the transcript with word-level timings and a WebVTT subtitle track. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/whisper/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 - Whisper

Request Code

POST https://gateway.pixazo.ai/whisper/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/whisper/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/whisper/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/whisper/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": "whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

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/whisper/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": "whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "whisper",
  "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": "whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "whisper",
  "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.
`task`	No	string	`transcribe`	`transcribe`, `translate`	`transcribe` keeps the spoken language; `translate` renders English regardless of the source.
`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. Detection is reported back as `transcription_info.language` with a confidence.
`vad_filter`	No	boolean	`false`	`true`, `false`	Drop silence before transcribing. Useful on long recordings with gaps.
`initial_prompt`	No	string	—	up to 2,000 characters	Bias the model toward expected wording — names, jargon, spellings.

Voices

Note it can hallucinate a short phrase on recordings that contain no speech — a known Whisper behaviour, not a fault of the API.

Example Request

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

Example Response

{
  "request_id": "whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/whisper_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/whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "whisper_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "whisper",
  "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 $0.0005 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	$0.0005
A 45-second clip	1	$0.0005
A 3-minute narration	3	$0.0015
A 10-minute narration	10	$0.005

Failed requests are not billed.

Whisper API Pricing

Your request will cost $0.0005 per minute of audio transcribed.

an hour of audio is about three cents

equivalent to $0.03 per hour of audio

⚡ Performance

Live usage measured on Pixazo's gateway, split by model version. Generation time is how long a generation takes end-to-end (lower is better). Success rate is the percent of generations that complete (higher is better).

Show data for the last

Generations

2,500last 30d

~83 per day

Success rate

88.0%

of completed generations

Generation time

86.4savg

p95 84.7s

Requests

Jul 28max 500Aug 26

Whisper Large v3 TurboAvg 67/day

WhisperAvg 7/day

GPT-4o TranscribeAvg 7/day

Whisper Tiny EnglishAvg 3/day

Generation Time

Jul 28max 99.1sAug 26

Whisper Large v3 TurboAvg 86.9s

WhisperAvg 74.4s

GPT-4o TranscribeAvg 89.1s

Whisper Tiny EnglishAvg 83.4s

Error Rate

Jul 28max 50.0%Aug 26

Whisper Large v3 TurboAvg 10.0%

WhisperAvg 50.0%

GPT-4o TranscribeAvg 0.0%

Whisper Tiny EnglishAvg 0.0%

〰 Uptime

Percent of generations that succeeded over the selected period, per model version.

Avg. Success Rate (30d)

88.00%

across all generations of this model family

Uptime

Jul 28max 100%Aug 26

Whisper Large v3 TurboAvg 90.00%

WhisperAvg 50.00%

GPT-4o TranscribeAvg 100.00%

Whisper Tiny EnglishAvg 100.00%