Cartesia Voice Settings
# support
f
Hello there! There a voice settings for cartesia. Is there any way to integrate these settings into the VAPI Transient AI? With JSON Code or something? https://cdn.discordapp.com/attachments/1267436082375430268/1267436082635735080/Bildschirmfoto_2024-07-29_um_12.56.28.png?ex=66a8c755&is=66a775d5&hm=931c6a42b08c2d484ae1b9bf487d805cb0d5a8feaf92129b3301a15a87e36c9d&
v
message has been deleted
@fabi Hello! Absolutely, you can integrate custom voice settings for Cartesia into VAPI's Transient AI. You can use JSON to configure the settings and pass them through the API. If you have the JSON configuration ready, you can send it over, and I can guide you on how to integrate it. If you need help creating the JSON configuration, I can assist with that as well. Just let me know how you'd like to proceed!
You can continue this conversation by mentioning me in the message.
Got it. Tagging @User for additional help.
f
@Vapi what code do I have to add, here is the voice code: "voice": { "voiceId": "3f6e78a8-5283-42aa-b5e7-af82e8bb310c", "provider": "cartesia", "model": "sonic-multilingual", "language": "de", "inputPunctuationBoundaries": [ "." ], "inputReformattingEnabled": true, "inputPreprocessingEnabled": true, "inputMinCharacters": 40 },
v
@fabi To integrate these voice settings into the VAPI Transient AI, you would typically need to include this configuration in the API call that initializes or configures the voice service. The JSON code you provided would be part of the body of a POST request to the VAPI endpoint responsible for setting up the voice parameters. Here's an example of how you might structure your API call with the provided JSON:
Copy code
json
{
  "configuration": {
    "voice": {
      "voiceId": "3f6e78a8-5283-42aa-b5e7-af82e8bb310c",
      "provider": "cartesia",
      "model": "sonic-multilingual",
      "language": "de",
      "inputPunctuationBoundaries": [
        "."
      ],
      "inputReformattingEnabled": true,
      "inputPreprocessingEnabled": true,
      "inputMinCharacters": 40
    }
  }
}
You would send this JSON payload to the appropriate VAPI endpoint using an HTTP client or a tool like
curl
. The exact endpoint and method (e.g., POST, PUT) would depend on the VAPI documentation. If you need further assistance with the API call or have any specific questions about the integration, please let me know, and I'd be happy to help!
f
Okay, but how do I add for example the speed of the voice? This is the docs of cartesia: https://docs.cartesia.ai/user-guides/voice-control
For example: "emotion": [ "curiosity", "positivity:high" ]
s
Currently, speed parameter isn't available for the cartesia through streaming.
m
@Sahil I found this on Cartesia website and streaming does support the speed: https://docs.cartesia.ai/api-reference/endpoints/stream-speech-bytes
s
I think they recently added it. Let me forward this to team and get this added
6 Views