Voice library
# support
h
In the Voice library, there is a Czech voice "Czech (M) deep voice" with the ID Mhq3uyDohpqKOg4UMdg9 (see image), but it cannot be found when using the assistant. It is also not available from other providers. Where can I find/activate it, please? For our needs, this voice sounds really excellent! https://cdn.discordapp.com/attachments/1324030604638949447/1324030604806983710/Snimek_obrazovky_1-1-2025_16113_dashboard.vapi.ai.jpeg?ex=6776ab17&is=67755997&hm=c94b0de1788c2a02ca234fc05d1fee28e13dabe9fb96444ee98b3c9a6c9d080b&
v
@happy.sun I'm glad to hear that you're interested in using the Czech voice "Czech (M) deep voice" with the ID Mhq3uyDohpqKOg4UMdg9 for your assistant. To activate and use this voice, you'll need to update the voice property in your assistant configuration with the provider and voiceId of the Czech voice you're interested in. Here's how you can update the configuration:
Copy code
json
{
  "voice": {
    "provider": "deepgram",
    "voiceId": "Mhq3uyDohpqKOg4UMdg9"
  }
}
Please ensure that you replace the
provider
and
voiceId
with the correct values for the Czech voice you want to use. If you've already done this and the voice is still not available, it's possible that there may be an issue with the voice library or the provider's availability. If you continue to have trouble finding or activating this voice, please reach out to support for more information on this specific voice and its availability. They will be able to provide you with the most up-to-date information and assist you further.
You can continue this conversation by mentioning me in the message.
Got it. Tagging @User for additional help.
@Shubham Bajaj can you check this, please? Thanks!
s
@happy.sun checking with team about this.
@Shubham Bajaj Do you have any info please? Thank you.
s
@happy.sun for this issue we are working on it, and it will be fixed in our next frontend release.
No, they are not completely different, but there is a slight difference in tone. This is expected because one voice is generated in real-time and optimised for latency, whereas the voice you heard in 11Labs is pre-recorded or generated just-in-time without any optimisation for latency.
5 Views