What Is a Voice Profile?
A Voice Profile bundles three things into a single reusable configuration:- Speech-to-Text (STT) - transcribes the caller’s audio into text
- Text-to-Speech (TTS) - converts agent text into natural-sounding audio
- Voice - the specific voice identity (gender, accent, character) used for TTS output
Listing Voice Profiles via SDK
VoiceProfile fields
Getting a Single Profile
Choosing the Right Profile
By use case
By latency
Total call latency has three components: STT transcription + LLM thinking + TTS synthesis.- Choose
quality == "high"when voice naturalness matters more than speed - Choose
quality == "standard"for latency-sensitive or high-volume deployments - Check
latency_mson the profile object for the estimated end-to-end figure
Using a Profile When Creating a Speech Pipe
Passprofile_id directly when creating or updating a Speech Pipe:
Switching a Profile on an Existing Speech Pipe
Next Steps
Speech Pipe
Attach a voice profile when creating or updating a Speech Pipe.
SDK Setup
Install the SDK and configure your runner process.