Cartesia TTS API
Generates speech audio from the provided text using Cartesia's Text-to-Speech service
textstring
Length
1 <= length <= 10000
voice?string
The ID of the voice to use
Default
"f9a4b3a6-b44b-469f-90e3-c8e19bd30e99"
model?string
The ID of the model to use for the generation
Default
"sonic-2"
tokenstring
Cartesia API key for authentication
Length
1 <= length
language?string
The language that the given voice should speak the transcript in
Default
"zh"
Value in
"en" | "fr" | "de" | "es" | "pt" | "zh" | "ja" | "hi" | "it" | "ko" | "nl" | "pl" | "ru" | "sv" | "tr"
duration?number
The maximum duration of the audio in seconds
Range
0 < value
speed?string
Speed setting for the model
Default
"normal"
Value in
"slow" | "normal" | "fast"
pronunciation_dict_ids?array<string>
A list of pronunciation dict IDs to use for the generation
output_format?object & object & object
Audio output format configuration
Default
{"container":"mp3","bit_rate":64000,"sample_rate":44100}
Response Body
curl -X POST "https://edge-workers.laplace.cn/laplace/tts-cartesia" \
-H "Content-Type: application/json" \
-d '{
"text": "Hello, world!",
"token": "string"
}'
null
{
"success": false,
"message": "string"
}
{
"success": false,
"message": "string"
}