The category of the voice. Possible values:
premade - Pre-made voice
cloned - Cloned voice
generated - Generated voice
professional - Professional voice
The description of the voice.
Labels associated with the voice. Common keys include:
language - The language of the voice
accent - The accent type
gender - The gender of the voice
age - The age range
The preview URL of the voice audio sample.
List of audio samples associated with the voice. Each sample includes:
sample_id - Unique identifier for the sample
file_name - Original filename
mime_type - MIME type of the audio
size_bytes - Size in bytes
hash - Hash of the sample
The current settings for the voice, including:
stability - Voice stability (0.0 to 1.0)
similarity_boost - Similarity enhancement (0.0 to 1.0)
style - Style exaggeration (0.0 to 1.0)
speed - Speech speed multiplier
use_speaker_boost - Whether speaker boost is enabled
Fine-tuning information for professional voice clones.
Information about voice sharing settings.
high_quality_base_model_ids
The base model IDs for high-quality voices.
verified_languages
List[VerifiedVoiceLanguageResponseModel]
The verified languages for the voice.
The IDs of collections this voice belongs to.
The safety controls applied to the voice.
voice_verification
VoiceVerificationResponse
Voice verification status and details.
The permission level on this voice resource.
Whether the current user is the owner of the voice.
Whether the voice is a legacy voice.
Whether the voice is a mixed voice.
Timestamp when the voice was marked as favorite (Unix time).
The creation time of the voice (Unix time).
Whether the voice is bookmarked by the current user. Only relevant for community (library-copied) voices.
The subscription tiers the voice is available for.