Skip to main content

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
When you attach a voice profile to a Speech Pipe, every call that Speech Pipe handles uses that configuration automatically - including failover if a provider goes down.
Voice profile pipeline diagram showing caller speech passing through STT, dialog machine text handling, TTS plus voice, and caller playback.
Voice profiles are managed by Unpod. You browse and select from the available list - you do not configure STT/TTS providers directly.

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_ms on the profile object for the estimated end-to-end figure

Using a Profile When Creating a Speech Pipe

Pass profile_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.