> For the documentation index, fetch https://sync.so/docs/llms.txt. Append .md to a page URL for Markdown. Documentation-search MCP: https://sync.so/docs/_mcp/server.

# Generate Text-to-Speech

POST https://api.sync.so/v2/tts
Content-Type: application/json

Synthesize speech from a script and get back a hosted audio URL. The returned url can be reused as an audio input in POST /v2/generate to lip sync the synthesized take. voiceId accepts an ElevenLabs voice id (discover via GET /v2/voices) or the id of a voice cloned via POST /v2/voices. Free-tier keys share the monthly ElevenLabs allowance; paid plans are billed per use.

A voiceId that does not resolve returns a 422 with errorCode voice_not_found. If a voice from your own ElevenLabs account stops resolving, the connected API key may be invalid — provider failures surface errorCode elevenlabs_api_key_invalid (reconnect it in Settings > Integrations) or elevenlabs_quota_exceeded (402) when your own ElevenLabs quota is exhausted. Temporary ElevenLabs provider failures return errorCode elevenlabs_service_unavailable: 504 for provider timeouts and 503 for other provider outages. Retry those requests with backoff and include the requestId if you contact support. A voice with an unresolved ElevenLabs restriction returns errorCode voice_verification_required or voice_blocked (both normally 422, or 400 when the pre-synthesis check was unavailable), or voice_access_denied (400). The required action depends on the code and on whether the voice is from your own connected ElevenLabs account — see the Error Handling guide.

Reference: https://sync.so/docs/api-reference/api/tts-api/create

## Authentication

- `x-api-key` header (required) — API Key authentication via header

## Servers

- `https://api.sync.so` (Default, default)
- `https://dev-api.sync.so` (dev)
- `http://localhost:3001` (local)

## Request

### Body (application/json)

This endpoint expects a CreateTtsRequest.

- `script` (string, required) — The text to synthesize into speech (1–5,000 characters).
- `voiceId` (string, required) — A voice id to synthesize with — either an ElevenLabs voice id (discover via GET /v2/voices) or the id of a voice cloned via POST /v2/voices.
- `provider` (enum, required) — The voice provider to synthesize with. Currently `elevenlabs`.
  - Allowed values: `elevenlabs`
- `stability` (double, optional) — Voice stability (0-1). Higher is more consistent, lower is more expressive.
- `similarityBoost` (double, optional) — How closely the synthesized audio matches the original voice (0-1).

## Response

### 200

TTS audio generated successfully

- `id` (string, required) — A unique identifier for the synthesized audio.
- `url` (string, required) — The hosted URL of the synthesized audio. Reuse it as an audio input in POST /v2/generate to keep the same take across generations.
- `duration` (double, required) — Duration of the synthesized audio in seconds.

## Errors

### 401 Unauthorized Error

Unauthorized - Invalid or missing authentication

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

### 402 Payment Required Error

Payment Required - Feature requires higher plan

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

### 400 Bad Request Error

Bad Request - Invalid input or unsupported model

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

### 422 Unprocessable Entity Error

Unprocessable Entity - The requested generation is not downloadable (generation_not_downloadable), or submit-time validation failed (e.g. inaccessible media, invalid segments, a projectId/voiceId/assetId that does not resolve in your organization, or a file exceeding the plan size limit). The body carries a stable errorCode and, where applicable, the failing field.

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

### 503 Service Unavailable Error

Service Unavailable - A sync. labs service or provider dependency is temporarily unavailable. The body carries a stable errorCode such as elevenlabs_service_unavailable or controller_dependency_error. Keyed generation creates may return IDEMPOTENCY_OUTCOME_UNKNOWN when acceptance needs reconciliation, or IDEMPOTENCY_UNAVAILABLE when new keyed admission is disabled. Preserve the same key and payload; do not bypass protection. generation_admission_paused means new generation requests are paused for maintenance; generation_admission_unavailable means the API can't confirm it is accepting them. Retry after Retry-After.

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

### 504 Gateway Timeout Error

Gateway Timeout - A sync. labs service or provider dependency timed out. The body carries a stable errorCode such as elevenlabs_service_unavailable or controller_timeout.

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

### 500 Internal Server Error

Internal Server Error - An unexpected failure on our side. The body carries errorCode internal_error and a requestId; include the requestId when contacting support.

- `message` (GenerationErrorMessage, required) — A message describing the error.
- `statusCode` (double, required) — The type of error that occurred.
- `errorCode` (string, optional) — Stable, machine-readable error code (e.g. project_not_found, voice_not_found, concurrency_limit_reached). Branch your error handling on this, not on the message text. The full catalog of codes with messages and suggested fixes is served unauthenticated at GET /v2/errors.
- `suggestion` (string, optional) — A suggested fix an agent can act on.
- `field` (string, optional) — The request field the error refers to, when the failure is tied to a specific field (e.g. projectId, voiceId, input[].assetId).
- `docsUrl` (string, optional) — Link to the documentation page for the failing operation.
- `requestId` (string, optional) — Present on unexpected 500 responses. Include it when contacting support so the failing request can be located directly.
- `generationId` (string, optional) — Original generation ID when available for an uncertain keyed submission. Poll this ID; do not create another action to bypass IDEMPOTENCY_OUTCOME_UNKNOWN.
- `dialogueEditSection` (DialogueEditRetimeFailureSection, optional) — For dialogue_edit_removal_too_large: the section to change, when it can be identified. Create a new dialogue edit preview before submitting again.

## Types

### GenerationErrorMessage

A message describing the error.

### DialogueEditRetimeFailureSection

The dialogue-edit section that removes too much speech to stay in sync.

- `slotIndex` (integer, required) — Zero-based index of the section in the preview's `resultSlots`.
- `sourceStartMs` (integer, optional) — Start of the section in the source video, in absolute milliseconds.
- `sourceDurationMs` (integer, optional) — Length of the section in the source video, in milliseconds.

## Examples

**Request**

```json
{
  "script": "Hey — thanks for trying sync. labs.",
  "voiceId": "EXAVITQu4vr4xnSDxMaL",
  "provider": "elevenlabs"
}
```

**Response**

```json
{
  "id": "6533643b-aceb-4c40-967e-d9ba9baac39e",
  "url": "https://assets.sync.so/docs/example-tts.mp3",
  "duration": 2.1
}
```

**SDK Code**

```python
import requests

url = "https://api.sync.so/v2/tts"

payload = {
    "script": "Hey — thanks for trying sync. labs.",
    "voiceId": "EXAVITQu4vr4xnSDxMaL",
    "provider": "elevenlabs"
}
headers = {
    "x-api-key": "<apiKey>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.sync.so/v2/tts';
const options = {
  method: 'POST',
  headers: {'x-api-key': '<apiKey>', 'Content-Type': 'application/json'},
  body: '{"script":"Hey — thanks for trying sync. labs.","voiceId":"EXAVITQu4vr4xnSDxMaL","provider":"elevenlabs"}'
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.sync.so/v2/tts"

	payload := strings.NewReader("{\n  \"script\": \"Hey — thanks for trying sync. labs.\",\n  \"voiceId\": \"EXAVITQu4vr4xnSDxMaL\",\n  \"provider\": \"elevenlabs\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-api-key", "<apiKey>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.sync.so/v2/tts")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<apiKey>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"script\": \"Hey — thanks for trying sync. labs.\",\n  \"voiceId\": \"EXAVITQu4vr4xnSDxMaL\",\n  \"provider\": \"elevenlabs\"\n}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.sync.so/v2/tts")
  .header("x-api-key", "<apiKey>")
  .header("Content-Type", "application/json")
  .body("{\n  \"script\": \"Hey — thanks for trying sync. labs.\",\n  \"voiceId\": \"EXAVITQu4vr4xnSDxMaL\",\n  \"provider\": \"elevenlabs\"\n}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.sync.so/v2/tts', [
  'body' => '{
  "script": "Hey — thanks for trying sync. labs.",
  "voiceId": "EXAVITQu4vr4xnSDxMaL",
  "provider": "elevenlabs"
}',
  'headers' => [
    'Content-Type' => 'application/json',
    'x-api-key' => '<apiKey>',
  ],
]);

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

```csharp
using RestSharp;

var client = new RestClient("https://api.sync.so/v2/tts");
var request = new RestRequest(Method.POST);
request.AddHeader("x-api-key", "<apiKey>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{\n  \"script\": \"Hey — thanks for trying sync. labs.\",\n  \"voiceId\": \"EXAVITQu4vr4xnSDxMaL\",\n  \"provider\": \"elevenlabs\"\n}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "x-api-key": "<apiKey>",
  "Content-Type": "application/json"
]
let parameters = [
  "script": "Hey — thanks for trying sync. labs.",
  "voiceId": "EXAVITQu4vr4xnSDxMaL",
  "provider": "elevenlabs"
] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.sync.so/v2/tts")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```