Voices
Get Voices
Retrieve voices for the authenticated workspace, filtered by model tier
GET
Request
Headers
string
required
Bearer token with your API key
Query Parameters
string
default:"quality"
Voice model tier to return. Accepted values:
"quality"(default) — returns60db Qualityprofessional voices"fast"— returns60db Fastcloned voices
"quality".Response
boolean
Indicates whether the request was successful
string
Response message describing the result
array
Array of voice objects matching the requested model tier
string
Resolved model tier applied to the response:
"quality" or "fast"string
Unique voice identifier (UUID format)
string
Display name of the voice
string
TTS model used by the voice:
"60db Fast" or "60db Quality"object
Metadata labels describing the voice attributes
string
ISO language code (e.g.,
"en", "hi", "ar", "fr", "de", "es", "it", "nl", "pl", "pt", "bn", "gu", "kn", "ml", "mr", "pa", "ta", "te")string
Full language name (e.g.,
"English", "Hindi", "Arabic")string
Voice gender:
"male" or "female"string
Voice accent:
"American", "British", "Indian", or "Neutral"string | null
Optional description of the voice.
null if not provided.array
Recommended use case categories for the voice. Possible values include:
"Entertainment/TV", "IVR/Call Center", "Finance/Banking", "Conversational", "Medical/Healthcare", "Religious/Spiritual", "Corporate/Business", "Government/Public Sector", "Social Media", "Documentary", "Travel/Tourism", "Kids/Children", "Legal", "Audiobook", "Gaming", "Podcast", "Advertisement", "E-Learning", "News/Journalism", "Sports", "Animation", "Professional Cloning"