Pixazo API→Models→Text to Speech API→Deepgram

Deepgram Aura 2 API, Deepgram Aura 1 API, Deepgram Nova 3 API: Pricing, Documentation

Deepgram Aura 2 API delivers a highly advanced text-to-speech solution engineered specifically for real-time conversational artificial intelligence applications. By combining deep learning architectures with optimized streaming protocols, the API transforms raw text into natural, human-like speech with exceptionally low latency. This high-speed performance makes it ideal for interactive voice agents, customer support bots, and dynamic media generation where instant responses are critical. The system features a diverse selection of premium, studio-quality voices that accurately replicate realistic intonations, rhythms, and vocal nuances. Designed for seamless developer integration, it provides scalable, efficient, and robust voice synthesis that elevates user engagement across digital platforms.

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 →

Deepgram Aura 2 English API Documentation

The newer Aura generation for English, with a much wider voice range and steadier delivery on long copy. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/deepgram-aura-2-en/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 - Deepgram Aura 2 English

Request Code

POST https://gateway.pixazo.ai/deepgram-aura-2-en/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/deepgram-aura-2-en/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/deepgram-aura-2-en/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/deepgram-aura-2-en/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": "deepgram-aura-2-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-aura-2-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/deepgram-aura-2-en/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": "deepgram-aura-2-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-aura-2-en",
  "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": "deepgram-aura-2-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "deepgram-aura-2-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
`text`	Yes	string	—	up to 10,000 characters	The text to speak.
`speaker`	No	string	model default	see the voice list above	Which voice to use. Each Aura model has its own voice set; a name from another model is rejected.
`encoding`	No	string	`mp3`	`mp3`, `opus`, `flac`, `aac`, `linear16`, `mulaw`, `alaw`	Audio codec. The file you receive is stored with the matching extension.
`container`	No	string	—	`none`, `wav`, `ogg`	Container to wrap the codec in. A container wins over the codec: `opus` in `ogg` is returned as `.ogg`.
`sample_rate`	No	integer	model default	8000 – 48000	Output sample rate in Hz.
`bit_rate`	No	integer	model default	codec dependent	Output bit rate.

Voices

41 voices including apollo, aurora, hermes, luna, mars, neptune, orion, saturn, thalia and vesta.

Example Request

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

Example Response

{
  "request_id": "deepgram-aura-2-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-aura-2-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/deepgram-aura-2-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "deepgram-aura-2-en_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-aura-2-en",
  "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.

Deepgram Aura 2 English API Pricing

Your request will cost $0.03 per 1,000 characters of input text.

about $0.03 for a 1,000-character paragraph

equivalent to $30 per 1M characters

2. Deepgram Aura 2 Spanish

Deepgram Aura 2 Spanish API Documentation

Aura 2 tuned for Spanish, with native Spanish voices rather than an English model reading Spanish text. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/deepgram-aura-2-es/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 - Deepgram Aura 2 Spanish

Request Code

POST https://gateway.pixazo.ai/deepgram-aura-2-es/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/deepgram-aura-2-es/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/deepgram-aura-2-es/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/deepgram-aura-2-es/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": "deepgram-aura-2-es_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-aura-2-es_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/deepgram-aura-2-es/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": "deepgram-aura-2-es_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-aura-2-es",
  "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": "deepgram-aura-2-es_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "deepgram-aura-2-es",
  "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 10,000 characters	The text to speak.
`speaker`	No	string	model default	see the voice list above	Which voice to use. Each Aura model has its own voice set; a name from another model is rejected.
`encoding`	No	string	`mp3`	`mp3`, `opus`, `flac`, `aac`, `linear16`, `mulaw`, `alaw`	Audio codec. The file you receive is stored with the matching extension.
`container`	No	string	—	`none`, `wav`, `ogg`	Container to wrap the codec in. A container wins over the codec: `opus` in `ogg` is returned as `.ogg`.
`sample_rate`	No	integer	model default	8000 – 48000	Output sample rate in Hz.
`bit_rate`	No	integer	model default	codec dependent	Output bit rate.

Voices

10 voices: sirio, nestor, carina, celeste, alvaro, diana, aquila, selena, estrella, javier.

Example Request

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

Example Response

{
  "request_id": "deepgram-aura-2-es_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-aura-2-es_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/deepgram-aura-2-es_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "deepgram-aura-2-es_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-aura-2-es",
  "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.

Deepgram Aura 2 Spanish API Pricing

Your request will cost $0.03 per 1,000 characters of input text.

native Spanish voices, about $0.03 per 1,000 characters

equivalent to $30 per 1M characters

3. Deepgram Aura 1

Deepgram Aura 1 API Documentation

Context-aware English speech that applies natural pacing, emphasis and fillers based on the text around each phrase. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/deepgram-aura-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 - Deepgram Aura 1

Request Code

POST https://gateway.pixazo.ai/deepgram-aura-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/deepgram-aura-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/deepgram-aura-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/deepgram-aura-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": "deepgram-aura-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-aura-1_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/deepgram-aura-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": "deepgram-aura-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-aura-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": "deepgram-aura-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "deepgram-aura-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 10,000 characters	The text to speak.
`speaker`	No	string	model default	see the voice list above	Which voice to use. Each Aura model has its own voice set; a name from another model is rejected.
`encoding`	No	string	`mp3`	`mp3`, `opus`, `flac`, `aac`, `linear16`, `mulaw`, `alaw`	Audio codec. The file you receive is stored with the matching extension.
`container`	No	string	—	`none`, `wav`, `ogg`	Container to wrap the codec in. A container wins over the codec: `opus` in `ogg` is returned as `.ogg`.
`sample_rate`	No	integer	model default	8000 – 48000	Output sample rate in Hz.
`bit_rate`	No	integer	model default	codec dependent	Output bit rate.

Voices

12 voices: angus, asteria, arcas, orion, orpheus, athena, luna, zeus, perseus, helios, hera, stella.

Example Request

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

Example Response

{
  "request_id": "deepgram-aura-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-aura-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/deepgram-aura-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "deepgram-aura-1_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-aura-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.

Deepgram Aura 1 API Pricing

Your request will cost $0.015 per 1,000 characters of input text.

the cheapest voice in the range at $0.015 per 1,000 characters

equivalent to $15 per 1M characters

4. Deepgram Nova 3

Deepgram Nova 3 API Documentation

Deepgram's Nova 3 transcription. Returns the transcript with per-word timings and a confidence score, and can label speakers when diarize is on. Asynchronous: submit returns a request_id; poll the status endpoint until the request is COMPLETED, then download the audio.

POST https://gateway.pixazo.ai/deepgram-nova-3/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 - Deepgram Nova 3

Request Code

POST https://gateway.pixazo.ai/deepgram-nova-3/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/deepgram-nova-3/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/deepgram-nova-3/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/deepgram-nova-3/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": "deepgram-nova-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-nova-3_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/deepgram-nova-3/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": "deepgram-nova-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-nova-3",
  "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": "deepgram-nova-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "deepgram-nova-3",
  "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 punctuate, diarize and smart_format flags shape the output.

Example Request

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

Example Response

{
  "request_id": "deepgram-nova-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/deepgram-nova-3_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/deepgram-nova-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx' \
  -H 'Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY'

Completed response

{
  "request_id": "deepgram-nova-3_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "deepgram-nova-3",
  "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 $0.0052 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	$0.0052
A 45-second clip	1	$0.0052
A 3-minute narration	3	$0.0156
A 10-minute narration	10	$0.052

Failed requests are not billed.

Deepgram Nova 3 API Pricing

Your request will cost $0.0052 per minute of audio transcribed.

an hour of audio is $0.31

equivalent to $0.312 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

1,900last 30d

~63 per day

Success rate

84.2%

of completed generations

Generation time

84.5savg

p95 99.3s

Requests

Jul 27max 300Aug 25

Deepgram Aura 2 EnglishAvg 23/day

Deepgram Aura 1Avg 20/day

Deepgram Aura 2 SpanishAvg 13/day

Deepgram Nova 3Avg 7/day

Generation Time

Jul 27max 2.3minAug 25

Deepgram Aura 2 EnglishAvg 79.0s

Deepgram Aura 1Avg 93.3s

Deepgram Aura 2 SpanishAvg 74.2s

Deepgram Nova 3Avg 87.7s

Error Rate

Jul 27max 100.0%Aug 25

Deepgram Aura 2 EnglishAvg 28.6%

Deepgram Aura 1Avg 0.0%

Deepgram Aura 2 SpanishAvg 25.0%

Deepgram Nova 3Avg 0.0%

〰 Uptime

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

Avg. Success Rate (30d)

84.21%

across all generations of this model family

Uptime

Jul 27max 100%Aug 25

Deepgram Aura 2 EnglishAvg 71.43%

Deepgram Aura 1Avg 100.00%

Deepgram Aura 2 SpanishAvg 75.00%

Deepgram Nova 3Avg 100.00%