Create audio
HTTP request
POST /ai/audio_generation
Authorization
Include your ACCESS TOKEN in HTTP Authorization header.
Request Parameters
prompt
String
The text you wish to convert into speech. Example: "Hello, my name is Suno".
configs
JSON
This parameter is a JSON object encompassing a variety of settings you can adjust to customize the image generation process. It includes several parameters, which we will describe next, allowing you to control different aspects of the generation.
model
String
Specifies the AI model used for generating the speech. Default is "bark".
User Guide
Craft a Clear Prompt: Start by writing the text that you want to be spoken. This text should be clear and well-structured, as it will be directly converted into speech. Consider the flow and natural pauses in speech to make the output sound more realistic.
Generate and Evaluate: Once you've crafted your prompt, generate your speech. Listen to the audio output carefully to assess its quality, clarity, and how well it matches your expectations.
Refine Your Prompt for Naturalness: If the speech doesn't sound as natural or expressive as you'd like, consider revising your prompt. Adding punctuation, changing sentence structures, or even specifying the tone can help guide the AI to produce more natural-sounding speech.
Example Request
Parrot API
Response
Returns the ID of the successful task.
Last updated
Was this helpful?