> ## Documentation Index
> Fetch the complete documentation index at: https://api-docs.voicecheap.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Generate speech

> Create speech from text using a catalog or owned custom voice. Uses the same character credits and plan limits as the app. Returns a history ID and a temporary audio download URL. Reuse requestId to avoid a second generation.

Create speech from text using a catalog or owned custom voice. Uses the same character credits and plan limits as the app. Returns a history ID and a temporary audio download URL. Reuse requestId to avoid a second generation.

```http theme={null}
POST https://api.voicecheap.ai/v1/actions/tts_generate
```

## Authentication and permissions

**x-api-key** `string` *required*

Send a VoiceCheap API key in this header. Authorization: Bearer with the same API key is also supported. OAuth access tokens are accepted only by
MCP, not by this REST endpoint.

Required permissions: `tts:write`.

An active paid subscription is required. Permissions do not change team roles, resource ownership, media credits, or plan limits.

## Parameters

**requestId** `string`

Optional at the transport boundary: the server injects an identifier before validation when omitted. Supply your own stable UUID v4 to recover safely from a lost response.

Format: "uuid". Pattern: `^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-4[0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$`.

**text** `string` *required*

Text value.

Minimum length: 1. Maximum length: 128000.

**voice** `string` *required*

A voice selection ID from voices\_list, including clone: IDs for saved custom voices.

Minimum length: 1. Maximum length: 255.

**inputType** `string`

Text value.

Allowed values: "text", "pdf". Default: "text".

**instructionPreset** `string`

Text value.

Allowed values: "default", "cheerful", "calm", "narrator", "dramatic", "whisper", "energetic". Default: "default".

**instructions** `string`

Text value.

Maximum length: 300.

**speed** `number`

Numeric value.

Minimum: 0.5. Maximum: 2. Default: 1.

**sourceFileName** `string`

Text value.

Maximum length: 255.

> [accordion] Complete input schema
>
> The JSON Schema below preserves the exact field names, nested types, defaults, bounds, and accepted values exposed by discovery. Additional cross-field rules are listed in the operation notes.
>
> ```json theme={null}
> {
>   "type": "object",
>   "properties": {
>     "requestId": {
>       "description": "UUID v4 for this action. Reuse the same ID with identical arguments on retries.",
>       "type": "string",
>       "format": "uuid",
>       "pattern": "^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-4[0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$"
>     },
>     "text": {
>       "type": "string",
>       "minLength": 1,
>       "maxLength": 128000
>     },
>     "voice": {
>       "type": "string",
>       "minLength": 1,
>       "maxLength": 255,
>       "description": "A voice selection ID from voices_list, including clone: IDs for saved custom voices."
>     },
>     "inputType": {
>       "default": "text",
>       "type": "string",
>       "enum": ["text", "pdf"]
>     },
>     "instructionPreset": {
>       "default": "default",
>       "type": "string",
>       "enum": ["default", "cheerful", "calm", "narrator", "dramatic", "whisper", "energetic"]
>     },
>     "instructions": {
>       "type": "string",
>       "maxLength": 300
>     },
>     "speed": {
>       "default": 1,
>       "type": "number",
>       "minimum": 0.5,
>       "maximum": 2
>     },
>     "sourceFileName": {
>       "type": "string",
>       "maxLength": 255
>     }
>   },
>   "required": ["text", "voice"],
>   "additionalProperties": false
> }
> ```

## Idempotency

Use a UUID v4 in requestId or the Idempotency-Key HTTP header for each mutation. Reuse the same identifier and identical arguments after a network failure. If both are supplied, they must match. Replaying a saved request does not repeat the operation or charge another monthly call. Failed or interrupted requests are not restarted automatically.

Every mutation can return HTTP 202 when a retry finds the same request still running, even when its first execution is normally synchronous. If execution completed but resultStored is false, a retry returns HTTP 200 with saved request state instead of the original result. Retrieve the output through its domain history, result, or download action.

## Request examples

Replace example resource identifiers and media keys with values returned for your account. Keep the request identifier stable when retrying the same mutation.

```bash cURL theme={null}
curl --request POST 'https://api.voicecheap.ai/v1/actions/tts_generate' \
  --header "x-api-key: $VOICECHEAP_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{"requestId":"284a861a-4da8-4d67-ad48-8123e76c8e91","text":"Hello world.","voice":"933563129e564b19a115bedd57b7406a","inputType":"text","instructionPreset":"narrator","instructions":"Speak clearly and leave a short pause at the end.","speed":1,"sourceFileName":"launch-script.txt"}'
```

```javascript JavaScript theme={null}
const input = {
  requestId: '284a861a-4da8-4d67-ad48-8123e76c8e91',
  text: 'Hello world.',
  voice: '933563129e564b19a115bedd57b7406a',
  inputType: 'text',
  instructionPreset: 'narrator',
  instructions: 'Speak clearly and leave a short pause at the end.',
  speed: 1,
  sourceFileName: 'launch-script.txt',
};
const response = await fetch('https://api.voicecheap.ai/v1/actions/tts_generate', {
  method: 'POST',
  headers: {
    'x-api-key': process.env.VOICECHEAP_API_KEY,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify(input),
});
const body = await response.json();
if (!response.ok) throw new Error(body.code + ': ' + body.message);
console.log(body);
```

```python Python theme={null}
import os
import requests

response = requests.post(
    "https://api.voicecheap.ai/v1/actions/tts_generate",
    headers={"x-api-key": os.environ["VOICECHEAP_API_KEY"]},
    json={"requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91", "text": "Hello world.", "voice": "933563129e564b19a115bedd57b7406a", "inputType": "text", "instructionPreset": "narrator", "instructions": "Speak clearly and leave a short pause at the end.", "speed": 1, "sourceFileName": "launch-script.txt"},
    timeout=120,
)
body = response.json()
if not response.ok:
    raise RuntimeError(f"{body.get('code')}: {body.get('message')}")
print(body)
```

## Response

This operation returns HTTP 202 while running. Save requestId and poll action\_request\_get with that identifier and the original operation name. Polling states are running, completed, failed, and interrupted. A completed result can point to a separate media job; continue with the operation-specific status or output action.

Completed speech generation metadata and a temporary MP3 download URL. The handler does not return audio bytes.

```json HTTP 202 theme={null}
{
  "data": {
    "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91",
    "status": "running",
    "pollAction": "action_request_get",
    "pollAfterSeconds": 5
  },
  "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91"
}
```

```json HTTP 200 theme={null}
{
  "data": {
    "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91",
    "historyId": "722c80c6412edd4c3dcd625061e1c1feafbb0d54274d95fd8b5ca047f8cdd23d",
    "status": "completed",
    "characterCount": 12,
    "previewEndIndex": null,
    "downloadUrl": "https://files.example.com/launch-script-speech.mp3"
  },
  "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91"
}
```

```json HTTP 202 replay_running theme={null}
{
  "data": {
    "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91",
    "operation": "tts_generate",
    "createdAt": 1792144800000,
    "updatedAt": 1792144820000,
    "status": "running",
    "pollAfterSeconds": 5
  },
  "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91"
}
```

```json HTTP 200 replay_completed_without_result theme={null}
{
  "data": {
    "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91",
    "operation": "tts_generate",
    "createdAt": 1792144800000,
    "updatedAt": 1792144820000,
    "status": "completed",
    "resultStored": false,
    "message": "The action completed. Retrieve its output from the corresponding history or resource action."
  },
  "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91"
}
```

## Result fields

| Field | Description |
| - | - |
| `data.requestId` | UUID v4 supplied for the generation action. |
| `data.historyId` | Owned speech history ID: 64 lowercase hexadecimal characters, optionally prefixed with free- for an app preview. |
| `data.status` | completed when the speech result is ready. |
| `data.characterCount` | Number of characters in the full trimmed input text. |
| `data.previewEndIndex` | Character boundary of partial preview audio, or null for complete audio. Paid integration generation returns complete audio. |
| `data.downloadUrl` | Temporary MP3 download URL. Request a fresh one through tts\_download. |

## Recover and poll this request

Use the same identifier even after a lost connection. If resultStored is false, retrieve the output through the corresponding history, result, or download action. Never start a second generation merely to check progress.

```bash theme={null}
curl --request POST 'https://api.voicecheap.ai/v1/actions/action_request_get' \
  --header "x-api-key: $VOICECHEAP_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{"requestId":"284a861a-4da8-4d67-ad48-8123e76c8e91","operation":"tts_generate"}'
```

```json HTTP 200 theme={null}
{
  "data": {
    "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91",
    "operation": "tts_generate",
    "status": "completed",
    "createdAt": 1792144800000,
    "updatedAt": 1792144820000,
    "resultStored": true,
    "result": {
      "requestId": "284a861a-4da8-4d67-ad48-8123e76c8e91",
      "historyId": "722c80c6412edd4c3dcd625061e1c1feafbb0d54274d95fd8b5ca047f8cdd23d",
      "status": "completed",
      "characterCount": 12,
      "previewEndIndex": null,
      "downloadUrl": "https://files.example.com/launch-script-speech.mp3"
    }
  }
}
```

## Operation notes

* Use a UUID v4 requestId for this mutation and reuse it with identical arguments when retrying. Long-running actions first return a running request; this example is the completed handler result available from action\_request\_get.
* Choose voice from voices\_list. Dubbing voice IDs from dubbing\_voices\_list are a separate library.
* Text is trimmed. The schema accepts at most 128,000 characters; current Beginner and Starter plans allow 64,000 per generation, while Creator and higher plans allow 128,000. The current plan and available TTS character credits are checked again before generation.
* inputType defaults to text and can be text or pdf. Even with pdf, supply extracted text in text; this action does not accept a PDF upload or URL.
* instructionPreset defaults to default and supports default, cheerful, calm, narrator, dramatic, whisper, and energetic. instructions is optional and limited to 300 trimmed characters. speed defaults to 1 and ranges from 0.5 to 2.
* sourceFileName is optional metadata, limited to 255 trimmed characters, and determines the download filename.
* A successful repeated request replays saved audio without generating or charging for it again. URLs are temporary; use tts\_download for a fresh download.
* Speech history and custom voices belong to the authenticated account. Team billing does not grant access to another member’s speech or voices.

## Usage

Each successful invocation consumes one monthly API/MCP call. Media credits and the operation's own generation allowances also apply.

## Errors

| HTTP status | Code | Meaning or recovery |
| - | - | - |
| 400 | `CREDENTIAL_IN_QUERY` | Credentials were supplied in an access\_token or api\_key query parameter. Send credentials in headers. |
| 400 | `IDEMPOTENCY_CONFLICT` | The Idempotency-Key header and requestId body field must match. |
| 400 | `INVALID_REQUEST_ID` | Supply a UUID v4 requestId or Idempotency-Key. |
| 400 | `INVALID_VOICE` | The voice selection is invalid, is not owned by this account, or is not ready. |
| 400 | `TEXT_REQUIRED` | The script is empty after removing delivery control tags. |
| 400 | `TEXT_TOO_LONG` | The script exceeds the current plan’s per-generation character limit. |
| 400 | `VALIDATION_ERROR` | The input does not match the action schema; inspect details for field errors. |
| 400 | `VOICE_UNAVAILABLE` | The selected catalog voice is no longer available; choose an ID returned by voices\_list. |
| 401 | `API_KEY_EXPIRED` | The API key has expired. |
| 401 | `INVALID_API_KEY` | Provide a valid, unexpired API key. |
| 401 | `INVALID_CREDENTIAL` | The Authorization header is malformed or conflicts with x-api-key. |
| 401 | `MISSING_CREDENTIAL` | No usable header credential was supplied, or it exceeded 4096 characters. |
| 401 | `USER_NOT_FOUND` | The credential's account no longer exists. |
| 403 | `ACCOUNT_UNAVAILABLE` | The acting or billing account is unavailable or being deleted. |
| 403 | `AMBIGUOUS_TEAM_API_KEY` | The credential's user belongs to more than one team, so the billing context is ambiguous. |
| 403 | `INSUFFICIENT_SCOPE` | Grant every required permission or choose another credential. |
| 403 | `INTEGRATION_PLAN_UNSUPPORTED` | The account's integration limits could not be verified. |
| 403 | `PAID_PLAN_REQUIRED` | The current account no longer has a paid plan for integration speech generation. |
| 403 | `SUBSCRIPTION_REQUIRED` | Use an active paid subscription. |
| 403 | `TEAM_OWNER_NOT_FOUND` | The effective team owner account could not be found. |
| 409 | `CONCURRENT_ACTION_LIMIT_REACHED` | This account already has 10 integration actions running. Poll an existing request before starting another. |
| 409 | `IDEMPOTENCY_CONFLICT` | Reuse an identifier only with the same operation and arguments. |
| 409 | `TEXT_TO_SPEECH_GENERATION_IN_PROGRESS` | An identical speech request is still processing. |
| 409 | `TEXT_TO_SPEECH_REQUEST_CONFLICT` | This requestId was already used with different speech input. |
| 429 | `INTEGRATION_MONTHLY_LIMIT_REACHED` | Wait for the monthly reset or change plan. |
| 429 | `INTEGRATION_RATE_LIMIT_REACHED` | Wait for Retry-After when present and use backoff. |
| 429 | `TEXT_TO_SPEECH_CHARACTER_LIMIT_REACHED` | The script exceeds the combined included and purchased TTS characters available. |
| 500 | `INTERNAL_ERROR` | Check saved request state and resource history before deciding to retry a mutation. |
| 502 | `INTERNAL_ERROR` | The action could not be completed or its outcome could not be confirmed. Inspect request status and resource history before starting another generation. |
| 503 | `ACTION_RESULT_UNAVAILABLE` | The action ran but its result could not be saved. Inspect saved request state and resource history before starting a new generation. |
| 503 | `SERVER_RESTARTING` | The server is restarting. Retry shortly and keep the same request identifier for a mutation. |

```json theme={null}
{
  "code": "INSUFFICIENT_SCOPE",
  "message": "This credential does not permit the requested action.",
  "status": 403,
  "details": {
    "requiredScopes": ["tts:write"]
  }
}
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.