Skip to main content
A voice group (fka language group) is a group of languages and voices that your agents have access to. You can use the voice groups feature to create a set of languages with their associated voices and DTMF options. Then, you can link the voice group to one or more agents, and update the agents’ messages to include a menu based on the voice group so that the user can change languages if desired at the beginning of the conversation.

​
Create voice group

To create a new voice group, click “Voices” on the left navbar. voices_create.png
  • Voice group name: The name of the voice group (must be unique within organization)
  • Description (optional): Description of the voice group.
  • Languages: Here you can select which languages are associated with the voice group. For each language, you must enter a DTMF code (a number between 1 and 9, inclusive), select a voice provider, and select a voice from that provider. Note that your voice options are limited to voices that support the selected language. Each language in the group must be unique and have a unique DTMF code. The option “Skip first language when reading out language options” allows you to omit the first language in the group from the DTMF menu presented as part of the greeting message (see below). You can also configure speed and pitch (depending on if the voice being used supports it), both of which take decimal numbers. 
To give an agent the ability to understand a user’s request to speak in different languages:
  1. Create a voice group as outlined above.
  2. Navigate to the agent. Your voice group should appear as an option in the “Voices” dropdown on the agent edit screen. Select the voice group and save changes.
  3. Navigate to the agent’s message. Insert the tag {{ language.mode }} into the message (and/or the text of any message rules) where you would like the language selection menu to be delivered by the agent. Save changes.
Now, when a user converses with your agent, at the beginning of the conversation it will deliver its associated message as normal, but at the point at which you inserted the {{ language.mode }} tag, it will instead read off a menu automatically generated from the voice group linked to the agent.  For example, for the voice group with: 
English - DTMF 1
Spanish - DTMF 2
Chinese - DTMF 3
the menu would be as follows: 
For English, press 1.
Para Español, oprima el 2.
中文请按 3.
If the user had selected “Skip first language when reading out language options” when configuring the voice group, it would instead be 
Para Español, oprima el 2.
中文请按 3.

​
Available voices and languages

​
Google Cloud Text‑to‑Speech

VoiceGenderModelLanguages
AoedeFemaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
CharonMaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
FenrirMaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
KoreFemaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
LedaFemaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
OrusMaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
PuckMaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
ZephyrFemaleChirp 3 HDen‑US, ko‑KR, zh‑CN, es‑US, th‑TH, vi‑VN
en‑US‑Neural2‑DMaleNeural2en‑US
en‑US‑Neural2‑FFemaleNeural2en‑US
es‑US‑Neural2‑AFemaleNeural2es‑US
es‑US‑Neural2‑BMaleNeural2es‑US
ko‑KR‑Neural2‑AFemaleNeural2ko‑KR
vi‑VN‑Neural2‑AFemaleNeural2vi‑VN
cmn‑TW‑Wavenet‑AFemaleWaveNetcmn‑TW
yue‑HK‑Standard‑CFemaleStandardyue‑HK
en‑US‑Studio‑OFemaleStudioen‑US

​
OpenAI Text‑to‑Speech

VoiceGenderModelLanguages
AlloyMaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
AshMaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
CoralFemaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
EchoFemaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
FableFemaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
NovaFemaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
OnyxMaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
SageMaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN
ShimmerFemaleTTS‑1en‑US, ko‑KR, zh‑CN, fa‑IR, es‑US, th‑TH, vi‑VN

​
ElevenLabs

VoiceGenderModelLanguages
AliceFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
BillMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
BrianMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
CallumMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
CharlieMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
CharlotteFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
ChrisMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
DanielMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
EricMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
GeorgeMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
JessicaFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
LauraFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
LiamMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
LilyFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
MatildaFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
RiverMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
RogerMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
SarahFemaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
WillMaleeleven_flash_v2_5en‑US, ko‑KR, zh‑CN, es‑US
How to listen to AI voices in Console:
  • Log into the Syllable Console
  • Click the Voices tab, then select New Voice Group
  • Name your new Voice Group.
  • Select the default language.
  • Pick a voice provider.
  • Click the speaker icon to listen to a sample of the voice you want to hear.
  • Tweak the Voice Speed and Pitch to your liking. We recommend small increments to maintain a human timbre.

​
Pronunciations

Coming soon…