Skip to main content
POST
Generate speech for your target-language SRT on an existing transcribed project. Speech and optional lip sync use the normal media credits. Poll projects_status.

​
Authentication and permissions

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

​
Parameters

​
string
required
Text value.Minimum length: 1. Maximum length: 200. Pattern: ^[^/\\]+$.
​
boolean
Boolean value.
​
boolean
Boolean value.
​
number
Numeric value.Minimum: 1. Maximum: 70.
​
string
Text value.Allowed values: “cloning”, “custom”.
​
string
Text value.Minimum length: 1. Maximum length: 128.
​
boolean
Boolean value.
​
string
Text value.Allowed values: “translated”, “original”.
​
string
Text value.Allowed values: “studio”, “realistic”.
​
string
Text value.Allowed values: “standard”, “pro”, “studio”.
​
boolean
Boolean value.
​
object
JSON object. See the complete input schema for its nested fields.
​
array
List of values. See the complete input schema for its item structure.Maximum items: 100.
​
string
required
Text value.Allowed values: “afrikaans”, “albanian”, “amharic”, “arabic”, “armenian”, “assamese”, “azerbaijani”, “basque”, “belarusian”, “bengali”, “bosnian”, “bulgarian”, “catalan”, “croatian”, “czech”, “danish”, “dutch”, “english”, “british english”, “estonian”, “finnish”, “french”, “french canadian”, “galician”, “german”, “greek”, “gujarati”, “hebrew”, “hindi”, “hungarian”, “icelandic”, “indonesian”, “irish”, “italian”, “japanese”, “kannada”, “kazakh”, “khmer”, “korean”, “lao”, “latvian”, “lithuanian”, “macedonian”, “malay”, “malayalam”, “mandarin”, “marathi”, “mongolian”, “nepali”, “norwegian”, “persian”, “polish”, “portuguese”, “brazilian portuguese”, “pt_brazil”, “punjabi”, “romanian”, “russian”, “serbian”, “slovak”, “slovenian”, “spanish”, “swahili”, “swedish”, “tagalog”, “tamil”, “telugu”, “thai”, “turkish”, “ukrainian”, “urdu”, “vietnamese”, “welsh”, “yoruba”, “zulu”.
​
string
required
Text value.Minimum length: 1. Maximum length: 1000000.
​
string
Optional at the transport boundary: the server injects an identifier before validation when omitted. Supply your own stable UUID v4 to recover safely from a lost response.Format: “uuid”. Pattern: ^[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-4[0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}$.
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.

​
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.

​
Response

A successful first execution returns HTTP 200 with the operation result under data. A replay may return saved request state instead. The example shows one supported response, not every optional field. Returns the project and language-work identifiers after admitting speech generation from caller-supplied target-language SRT.

​
Result fields

​
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.
HTTP 200

​
Operation notes

  • translatedSrt is required and must contain valid SRT cues. This action requires a completed original transcript. Cues match the existing source segments by start time within 0.05 seconds, falling back to the largest time overlap; output timing always uses the original segment timeline.
  • The target-language work is reused or created. The supplied text is dubbed without automatic translation or SmartSync.
  • No source media is re-uploaded. The stored project provides duration and audio/video type.
  • This action does not accept sourceSrt, fileKey, a media URL, or webhookUrl.
  • voiceMode defaults to cloning. With voiceMode custom, use a catalog voice or a custom voice saved by the authenticated account; do not supply voiceCloningSettings. Team billing does not grant access to another member’s saved voices.
  • Optional subtitles, lipSyncMode, and translationTimeSkips require video input. Skipped ranges must remain within media duration, keepBackgroundMusic must be true, and keepOriginalVoice must be false.
  • lipSyncMode accepts standard, pro, or studio, subject to the plan and normal media-credit checks. Speech and lip sync do not become free because monthly API calls are unlimited.
  • Poll projects_status for the media workflow; fetch all language versions with projects_get.
  • A cue with no matching source segment or a source segment without supplied text can fail the background pipeline; inspect projects_status.error or projects_get translations after admission.

​
Usage

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

​
Errors