Speech-to-speech (EVI)Configuration

Voice

Guide to customizing the voice of the Empathic Voice Interface (EVI).

EVI supports a variety of voice options depending on your EVI version. This guide outlines these voice options and explains how to specify a voice in your EVI configuration.

Voice options

Voice options differ depending on which version of EVI you are using:

VersionDefaultVoice options
EVI 1ITO

Select from a fixed set of 3 base voices: ITO, KORA, and DACHER.

EVI 2ITO

Select from a fixed set of 8 base voices: ITO, KORA, DACHER, AURA, FINN, WHIMSY, STELLA, and SUNNY.

EVI 3None

Choose from over 100 voices available in Hume’s Voice Library or select from the custom voices you have designed or cloned.

EVI 1 and EVI 2 configurations will default to a preset voice if none is specified. For EVI 3 configurations, a voice must be specified.

Configure the voice in the UI

Specify a voice in your EVI config using the EVI Playground or through the API.

To change the voice used in your EVI config:

  1. Visit the EVI Playground.
  2. In the config panel, select the config you wish to update.
  3. Select a voice from your saved voices or from the Voice Library.
  4. Click Save to apply the change to your currently selected EVI config.

This is the simplest way to adjust and preview voice options in an interactive setting.

Specify a voice via the API

When creating or updating an EVI config via the API, include the voice field in the request body.

You can specify a voice in your request using either its id or name. Each voice belongs to a provider, which indicates the source of the voice and who can access it.

ProviderDescription
CUSTOM_VOICE

Select from designed or cloned voices you’ve saved to your account. These voices are private.

HUME_AI

Select from Hume’s shared Voice Library of predesigned voices. These voices are public.

If you omit the provider field, it defaults to CUSTOM_VOICE. To use a voice from the Voice Library, you must explicitly set the provider to HUME_AI.

1curl https://api.hume.ai/v0/evi/configs \
2 -H "X-Hume-Api-Key: $HUME_API_KEY" \
3 --json '{
4    "evi_version": "3",
5    "name": "Example Config",
6    "voice": {
7      "id": "9e068547-5ba4-4c8e-8e03-69282a008f04",
8      "provider": "HUME_AI"
9    }
10  }'

Resources

Voice Design Guide

See the Voice Design Guide for how to design and create custom voice.

Voice Cloning Guide

Create a voice clone from a live recording or an audio file.