Pixazo API→Models→Text to Speech API→Zonos2

Zonos 2 API: Pricing, Documentation

Zonos 2 API is a text-to-speech and voice synthesis API that enables developers to generate natural-sounding speech from text with support for voice cloning, multilingual speech generation, and expressive audio controls. It is designed to create high-quality voice outputs using short reference audio samples while offering customization over speaking style, pitch, speed, and emotional tone. The API can be integrated into applications such as virtual assistants, content creation tools, audiobooks, customer support systems, and accessibility solutions, delivering realistic and responsive speech generation through a scalable cloud-based interface.

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 →

Zonos 2 API Documentation

https://gateway.pixazo.ai/zonos-2/v1/zonos-2-request

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Zonos 2 generate request

Request Code

POST https://gateway.pixazo.ai/zonos-2/v1/zonos-2-request
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_API_KEY

{
  "reference_audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Reference.wav",
  "text": "Hello, this is a sample of my cloned voice speaking naturally.",
  "language": "en_us",
  "accurate_mode": true,
  "clean_speaker_background": false,
  "temperature": 1.15,
  "top_p": 0,
  "min_p": 0.18,
  "top_k": 106
}

import requests

url = "https://gateway.pixazo.ai/zonos-2/v1/zonos-2-request"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
}
data = {
    "reference_audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Reference.wav",
    "text": "Hello, this is a sample of my cloned voice speaking naturally.",
    "language": "en_us",
    "accurate_mode": true,
    "clean_speaker_background": false,
    "temperature": 1.15,
    "top_p": 0,
    "min_p": 0.18,
    "top_k": 106
}

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

const url = "https://gateway.pixazo.ai/zonos-2/v1/zonos-2-request";
const headers = {
  "Content-Type": "application/json",
  "Cache-Control": "no-cache",
  "Ocp-Apim-Subscription-Key": "YOUR_API_KEY"
};
const data = {
  "reference_audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Reference.wav",
  "text": "Hello, this is a sample of my cloned voice speaking naturally.",
  "language": "en_us",
  "accurate_mode": true,
  "clean_speaker_background": false,
  "temperature": 1.15,
  "top_p": 0,
  "min_p": 0.18,
  "top_k": 106
};

fetch(url, {
  method: "POST",
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data));

curl -X POST "https://gateway.pixazo.ai/zonos-2/v1/zonos-2-request" \
  -H "Content-Type: application/json" \
  -H "Cache-Control: no-cache" \
  -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  --data-raw '{
    "reference_audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Reference.wav",
    "text": "Hello, this is a sample of my cloned voice speaking naturally.",
    "language": "en_us",
    "accurate_mode": true,
    "clean_speaker_background": false,
    "temperature": 1.15,
    "top_p": 0,
    "min_p": 0.18,
    "top_k": 106
  }'

Output

{
  "request_id": "zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Zonos 2 generate request

Parameter	Required	Type	Default	Allowed values / range	Description
reference_audio_url	Yes	string	—	—	URL of the reference audio to clone the voice from. Supported formats: MP3, OGG, WAV, M4A, AAC.
text	No	string	"Fal" is the fastest solution for your audio generation.	—	Text to synthesize in the cloned voice. If omitted, the provider's default sample sentence is used.
language	No	string	"en_us"	"en_us", "en_gb", "fr_fr", "de", "es", "it", "pt_br", "ja", "cmn", "ko"	Text-normalization language code. Codes outside the supported list are accepted but skip text normalization.
accurate_mode	No	boolean	true	—	True = closer voice match; false = more expressive delivery.
clean_speaker_background	No	boolean	false	—	Tells the model the reference audio has a clean background (no background noise). Set true only when the sample is clean.
temperature	No	float	1.15	0–2	Sampling temperature (0–2). Higher values increase randomness.
top_p	No	float	0	0–1	Controls how varied the output is by limiting choices to the most likely options (0-1). Lower values are more focused; 0 turns this off.
min_p	No	float	0.18	0–1	Filters out very unlikely options during generation (0-1). Higher values keep only the most probable choices, making output more predictable.
top_k	No	integer	106	0–2048	Limits generation to the most likely options at each step (0-2048). Lower values make output more focused; 0 turns this off.
max_tokens	No	integer	—	1–6144	Maximum number of audio frames to generate (1–6144), which caps the output duration. Defaults to the model's context limit when omitted.
seed	No	integer	—	0–2147483647	Random seed that controls the generation's randomness. Reuse the same seed with identical settings to reproduce the same result; leave it empty for a different output each time.

Content Item Types & Limits

Type	Max	Format / Size	Description
audio	1	MP3, WAV	Reference voice (for cloning).

Example Request

{
  "reference_audio_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/Reference.wav",
  "text": "Hello, this is a sample of my cloned voice speaking naturally.",
  "language": "en_us",
  "accurate_mode": true,
  "clean_speaker_background": false,
  "temperature": 1.15,
  "top_p": 0,
  "min_p": 0.18,
  "top_k": 106
}

Response

{
  "request_id": "zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_API_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'zonos-2' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "zonos-2",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "zonos-2_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "zonos-2",
  "error": null,
  "output": {
    "media_url": ["https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/zonos-2_019dxxxx/output.wav"],
    "media_type": "audio/wav",
    "file_name": "output.wav",
    "file_size": 1245678
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Zonos 2 API Pricing

Your request will cost $0.01 per minute of audio.

about $0.10 for a 10-minute narration

equivalent to $0.60 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

68,200last 30d

~2,273 per day

Success rate

99.1%

of completed generations

Generation time

5.9minavg

p95 7.8min

Requests

Jul 8max 38,000Aug 6

Zonos 2Avg 2,273/day

Generation Time

Jul 8max 9.8minAug 6

Zonos 2Avg 5.9min

Error Rate

Jul 8max 100.0%Aug 6

Zonos 2Avg 0.9%

〰 Uptime

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

Avg. Success Rate (30d)

99.12%

across all generations of this model family

Uptime

Jul 8max 100%Aug 6

SuccessfulAvg 99.12%