Voice Library
Updated
The Voice Library provides a centralized catalog of voices available for use within Voice AI Text-to-Speech (TTS) configurations. Administrators can browse, search, filter, preview, and manage available voices before assigning them to TTS workflows.The Voice Library helps users discover voices across supported providers and quickly identify appropriate language, accent, gender, and provider configurations.
Intended Audience
Voice AI Administrators
Contact Center Administrators
Platform Administrators
Accessing Voice Library
Navigate to AI+ Studio from the Sprinklr launchpad.
Click the AI Use Cases card.
Navigate to Sprinklr Service tab.
Under Voice Workflow, select TTS. The Text-to-Speech Configurations page appears.
In the Text-to-Speech Configuration page, click + Configurations.
In the Voice Model section, click Explore Voices. The Voice Library page appears.
Understanding the Voice Library Page
The Voice Library includes the following information:
Field | Description |
Voice Name | Name of the voice available for selection |
Model Provider | Voice provider associated with the voice |
Key Management | Indicates the credential source used by the provider |
Voice Preview | Preview audio controls for the voice |
Language | Supported language |
Accent | Accent associated with the voice |
Gender | Voice classification provided by the speech provider |
Note: Field availability may vary by provider.
UI Capabilities
The following are some of the Voice Library UI capabilities:
Search for Voices - Use the search bar to find voices by:
Voice Name
Provider
Language
Accent
The results update automatically based on the search criteria entered.
Filter Voices - Use filters to narrow results by:
Model Provider (Amazon Polly, Azure OpenAI, Azure Speech, Eleven Labs, Google Chirp, Google Vertex)
Language
Accent
Gender
Key Management
Multiple filters can be combined to refine results.
Preview a Voice - Click the Play icon in the Voice Preview column. Voice previews help compare pronunciation, tone, and accent before selection.
Update My Voices
Select one or more voices and click Update My Voices to make the selected voices available in supported Text-to-Speech configurations.