---
title: Generate speech from text
url: https://developers.wpengine.com/docs/ai/api/reference/operations/createspeech/
image: https://developers.wpengine.com/og/docs/ai/api/reference/operations/createspeech.png
---

# Generate speech from text

POST

/v1/audio/speech

Select code sample

```php
<?php


$client = new \GuzzleHttp\Client();


$response = $client->request('POST', 'https://api.ai.wpengine.com/v1/audio/speech', [
  'body' => '{ "model": "google/gemini-2.5-flash-tts", "input": "example", "response_format": "pcm", "voice": "Achernar" }',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);


echo $response->getBody();
```

- Current environment

Converts text input to audio using a text-to-speech model. Returns binary audio data with the appropriate Content-Type header. Requires a valid WP Engine bearer token; API keys must carry the “speech:write” permission.

## Authorizations

- **[bearerAuth](https://developers.wpengine.com/docs/ai/api/reference/#bearerauth)**

## Request Bodyrequired

Media typeapplication/json

object

**model**

Optional model identifier. Defaults to a Gemini TTS model when omitted.

string

### Example

```
google/gemini-2.5-flash-tts
```

**input**

required

The text to convert to speech.

string

<= 5000 characters

**response_format**

Audio encoding format. “pcm” returns raw 16-bit linear PCM as received from the upstream provider. “wav” wraps the PCM data in a WAV container for direct browser playback. Omit for raw PCM (backward compatible).

string

Allowed values: pcm wav

### Example

```
wav
```

**voice**

The Chirp 3 HD voice to use for speech synthesis. Defaults to “Kore”. All 30 prebuilt voices are supported across 50+ languages.

string

default: Kore

Allowed values: Achernar Achird Algenib Algieba Alnilam Aoede Autonoe Callirrhoe Charon Despina Enceladus Erinome Fenrir Gacrux Iapetus Kore Laomedeia Leda Orus Pulcherrima Puck Rasalgethi Sadachbia Sadaltager Schedar Sulafat Umbriel Vindemiatrix Zephyr Zubenelgenubi

## Responses

### 200

Generated audio data

Select media type

string format: binary

### 400

Invalid request body or parameters. On agent create and update, error type “profile_unavailable” means the requested profile is not available to the caller.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 401

Missing or invalid bearer token

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

#### Headers

**WWW-Authenticate**

string

##### Example

```
Bearer realm="ai-services"
```

### 402

The account’s credit balance is exhausted. Grant or top up credits before retrying. Distinct from 429, which is edge rate limiting.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 403

The token is valid, but the request is forbidden. Error type “permission_error” means the token’s scope/permission is insufficient or the authenticated user is not authorized for the target account; “entitlement_required” means the account may not use WP Engine AI, with error_code giving why when known (not_eligible, terms_required, not_enabled or suspended) and portal_url where to fix it; “account_required” means no billing account could be resolved; and “billing_account_pending” means billing isn’t set up for the account yet, usually because its setup after AI was turned on hasn’t finished. Retry shortly. On /v1/chat/completions when content moderation is enabled, and on /v1/sessions/{session_id}/events, error type “content_policy_violation” instead means the request content was blocked by content moderation policy; that response never identifies which filter or category matched.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 413

Request body exceeds the 64 KiB limit

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 429

Rate limit exceeded. The request was throttled at the edge; wait and retry later. The response body is a short HTML page generated by the load balancer, not a structured JSON error — clients should rely on the 429 status code rather than parsing the body.

Media typetext/html

string

### 502

Upstream provider returned an error

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

### 503

A required dependency is temporarily unavailable. Retry after a short delay with exponential back-off. An entitlement lookup failure uses error type “entitlement_unavailable”. A model without complete rate coverage uses error type “model_unpriced”. A credit balance that can’t be read uses error type “balance_unavailable”.

Media typeapplication/json

object

**error**

required

object

**message**

required

string

**type**

required

string

**error_code**

Stable, machine-readable cause, set by routes that document their codes (the AI readiness and account AI routes, and an entitlement_required refusal, where it is one of not_eligible, terms_required, not_enabled or suspended); absent elsewhere and on errors from shared layers such as authentication. Clients must allow new codes.

string

**portal_url**

Where the customer can resolve the error, set on an entitlement_required refusal that has an error_code when one is configured.

string

**code**

required

integer

**request_id**

required

Correlation ID for this request, matching the X-Request-ID response header — a 32-character trace ID behind the load balancer, otherwise a UUID. Quote it in support reports.

string

#### Example

```json
{
  "error": {
    "type": "invalid_request_error",
    "request_id": "80f1e2c3a4b5c6d7e8f9a0b1c2d3e4f5"
  }
}
```

## Was this helpful?

Thanks for the feedback!

```json
{"@context":"https://schema.org","@graph":[{"@type":"WebSite","@id":"https://developers.wpengine.com/#website","name":"WP Engine Product Documentation","url":"https://developers.wpengine.com/","description":"Resources for developing, deploying, and scaling on WP Engine.","inLanguage":"en-US","keywords":["API documentation","product documentation","headless WordPress","managed WordPress hosting"],"publisher":{"@id":"https://wpengine.com/#organization"}}]}
```