Our Speech Generation API creates audio clips based on text prompts. These text prompts have a character limit of 4096, and the model produces one clip per prompt. The response contains a link to the generated audio clip.
A sample JSON response is shown below:
"output": [
{
"audio": [
{
"path": "file_path",
"url": "url_to_audio_clip"
}
]
}
]