Discussions
Voice clone limit
I am using the you APIs to clone the voice. I noticed that there is an limit to the audios you can clone. If I purchase your Enterprise Plan can this limit be customised according to the need.
Posted by schauhan 2 days ago
Custom ElevenLabs voice not working for agents
I added a custom voice for elevenlabs together with my request to create an agent by adding
```
"x-api-key-external": "myElevenLabsKey"
```
to the request and the voice in the presenter
```
"presenter": {
"type": "talk",
"voice": {
"type": "elevenlabs",
"voice_id": "0d7PmtkKJbIWQv5PVYJW"
},
"source_url": "https://test.com/output_image.png",
"thumbnail": "https://test.com/output_image.png"
},
```
And it doesn't work. The agent just never speaks.
Posted by joaopaulo.passos 2 days ago
j'arrive pas a mettre en français
j'arrive pas a mettre en français
Posted by ameur 2 days ago
Image cropping in the Agent API - stitch setting doesn't work
While setting up an agent, I tried doing
```
"presenter": {
"type": "talk",
"voice": {
"type": "elevenlabs",
"voice_id": "21m00Tcm4TlvDq8ikWAM"
},
"source_url": "https://test.com/image.jpg",
"thumbnail": "https://test.com/image.jpg",
"config": {
"stitch": True
}
}
```
However it is still cropping around the face. How to fix it for Agents?
<br>
Posted by joaopaulo.passos 2 days ago
can you please correct the text regarding the language?
can you please correct the text regarding the language?
Posted by gouva 3 days ago
How do I change the model used by Elevenlabs to generate my voice
I have got my custom voice working through elevenlabs but it does not sound correct unless I use the eleven_turbo_v2 model. I have tried implementing this in my code but to no avail. How can I use the eleven_turbo_v2 model for my voice?
<br>
{
"script": {
"type": "text",
"input": "I love to make simple API calls, this is my voice using AI and I like to talk like this lol",
"provider": {
"type": "elevenlabs",
"voice_id": "MY_VOICE_ID",
"model": "eleven_turbo_v2",
"voice_settings": {
"model": "eleven_turbo_v2",
"stability": 0.5,
"similarity_boost": 0.8,
"style": 0.0,
"use_speaker_boost": true
}
}
},
"source_url": "MY_SOURCE_URL",
"webhook": "<https://host.domain.tld/to/webhook">
}
Posted by Dax 3 days ago
Facial Expressions
How do I incorporate facial expressions using D-iD?
<br>
Posted by sbrowne988 3 days ago
How can I remove the D-iD watermark from AI Agent pro plan? And, AI agent not working on mobile.
1-Why are there many visible D-iD watermarks on the AI Agent I create using the Pro plan?
I'm on the paid pro plan for D-iD, so the watermarks should NOT be visible. Please remove the watermarks. Please watch the screenshare video below. It clearly shows the D-iD watermarks all over the background of the AI agent on my website. I've uninstalling and reinstalling the AI agent into my site but the watermarks are still visible. Also, in the email I sent to you I've included the screenshare .
<https://www.loom.com/share/de04127becb64533a55ca4983d443566?sid=30f002ed-a23b-4a80-8c3a-dde7ba7f858b>
2-Does AI Agent work on mobile?
I've emailed you a screenshot of my website from my iphone and you'll see that the AI agent is not showing on mobile.
Does the AI agent only work on Desktops/Laptops and not on mobile? Please let me know how to fix these two issues. Thank you.
<br>
Posted by sean 3 days ago
Inquiry on Real-Time Text Streaming Capabilities
I'm utilizing a Large Language Model (LLM) and I'm interested in streaming text inputs to enhance real-time processing with D-ID. Can D-ID support streaming inputs where it begins processing as soon as a word is submitted?
Does D-ID offer functionality for streaming content, such that it starts generating output immediately upon receiving an input word?
Posted by rodolfo 3 days ago
Knowledge base
What kinds of documents can I put into the knowledge base? Am I limited to text documents like PDFs, DOCs, etc.? Could I put video or audio into the knowledge base?
Posted by pharrity 4 days ago