Skip to content
CHAMELAION CHAMELAION CHAMELAION
DashboardGet API Key
API Reference

Video Translate

Endpoints for creating and polling asynchronous video translations.

Translate a remote video
video_translate.generate(VideoTranslateGenerateParams**kwargs) -> VideoTranslateGenerateResponse
POST/v1/video-translate/generate
Translate an uploaded video
video_translate.generate_with_media(VideoTranslateGenerateWithMediaParams**kwargs) -> VideoTranslateGenerateWithMediaResponse
POST/v1/video-translate/generate-with-media
ModelsExpand Collapse
class VideoTranslateGenerateResponse: …
request_id: str
formatuuid
status: Literal["success"]
class VideoTranslateGenerateWithMediaResponse: …
request_id: str
formatuuid
status: Literal["success"]

Video TranslateRequests

Endpoints for creating and polling asynchronous video translations.

Get a video translation request
video_translate.requests.retrieve(strid) -> RequestRetrieveResponse
GET/v1/video-translate/requests/{id}
List video translation requests
video_translate.requests.list(RequestListParams**kwargs) -> RequestListResponse
GET/v1/video-translate/requests
ModelsExpand Collapse
class RequestRetrieveResponse: …
id: str
formatuuid
config: Config

The request config as returned by the API. SRT content is replaced by metadata, speaker_voices keys are canonical speaker IDs, and other keys are returned unchanged.

source_srt: Optional[ConfigSourceSrt]

Public description of a supplied SRT. The subtitle content is never returned.

supplied: Literal[true]
file_name: Optional[str]
language: Optional[str]
speaker_voices: Optional[Dict[str, str]]
target_srts: Optional[Dict[str, ConfigTargetSrts]]
supplied: Literal[true]
file_name: Optional[str]
language: Optional[str]
tts_model: Optional[Literal["eleven_v4", "eleven_multilingual_v2"]]

The explicitly selected text-to-speech model. Omitted when the request used the default.

One of the following:
"eleven_v4"
"eleven_multilingual_v2"
created_at: datetime
formatdate-time
disable_background_audio: bool

Whether background audio was disabled for this request.

disable_lip_sync: bool

Whether lip sync was disabled for this request.

formality: bool
model: Literal["expressive", "classic"]

Product speech model selected for the request.

One of the following:
"expressive"
"classic"
status: Literal["queued", "uploading", "processing", 2 more]
One of the following:
"queued"
"uploading"
"processing"
"completed"
"failed"
target_languages: List[str]
error_message: Optional[str]

Present only when failed. A safe, bounded description, for example SRT or speaker validation errors found after the video was processed.

maxLength1001
finished_at: Optional[datetime]
formatdate-time
outputs: Optional[Dict[str, Outputs]]

Present only when completed, keyed by requested target language. URLs are signed on every read.

audio: str
formaturi
srt: str
formaturi
video: str
formaturi
reference_id: Optional[str]
source_language: Optional[str]

Explicit source language, or the detected one once processing starts.

started_at: Optional[datetime]
formatdate-time
webhook_url: Optional[str]

The configured terminal callback URL, when supplied.

formaturi
class RequestListResponse: …
data: List[Data]
id: str
formatuuid
config: DataConfig

The request config as returned by the API. SRT content is replaced by metadata, speaker_voices keys are canonical speaker IDs, and other keys are returned unchanged.

source_srt: Optional[DataConfigSourceSrt]

Public description of a supplied SRT. The subtitle content is never returned.

supplied: Literal[true]
file_name: Optional[str]
language: Optional[str]
speaker_voices: Optional[Dict[str, str]]
target_srts: Optional[Dict[str, DataConfigTargetSrts]]
supplied: Literal[true]
file_name: Optional[str]
language: Optional[str]
tts_model: Optional[Literal["eleven_v4", "eleven_multilingual_v2"]]

The explicitly selected text-to-speech model. Omitted when the request used the default.

One of the following:
"eleven_v4"
"eleven_multilingual_v2"
created_at: datetime
formatdate-time
disable_background_audio: bool

Whether background audio was disabled for this request.

disable_lip_sync: bool

Whether lip sync was disabled for this request.

formality: bool
model: Literal["expressive", "classic"]

Product speech model selected for the request.

One of the following:
"expressive"
"classic"
status: Literal["queued", "uploading", "processing", 2 more]
One of the following:
"queued"
"uploading"
"processing"
"completed"
"failed"
target_languages: List[str]
error_message: Optional[str]

Present only when failed. A safe, bounded description, for example SRT or speaker validation errors found after the video was processed.

maxLength1001
finished_at: Optional[datetime]
formatdate-time
outputs: Optional[Dict[str, DataOutputs]]

Present only when completed, keyed by requested target language. URLs are signed on every read.

audio: str
formaturi
srt: str
formaturi
video: str
formaturi
reference_id: Optional[str]
source_language: Optional[str]

Explicit source language, or the detected one once processing starts.

started_at: Optional[datetime]
formatdate-time
webhook_url: Optional[str]

The configured terminal callback URL, when supplied.

formaturi

Video TranslateVoices

Endpoints for creating and polling asynchronous video translations.

List voices for speaker assignment
video_translate.voices.list(VoiceListParams**kwargs) -> VoiceListResponse
GET/v1/video-translate/voices
ModelsExpand Collapse
class VoiceListResponse: …
voices: List[Voice]
application: str

Intended use case, for example narration.

default_name: str
description: str
gender: Literal["Male", "Female", "Other"]
One of the following:
"Male"
"Female"
"Other"
is_favorite: bool

Whether the authenticated account marked this voice as a favorite.

language: str

Primary language label.

name: str

Effective name (the account’s custom name when set, otherwise default_name).

voice_id: str

External voice ID. Use this value in config.speaker_voices.