How do I call the Speech API endpoint?

Send an HTTP request to https://api.acedata.cloud/v1/audio/speech with a Bearer token in the Authorization header. See the documentation for request parameters and response format.

What authentication does OpenAI generation require?

All Ace Data Cloud APIs use Bearer token authentication. Get your API key from the platform dashboard at https://platform.acedata.cloud and include it as: Authorization: Bearer YOUR_TOKEN

How much does OpenAI generation cost?

OpenAI generation uses pay-as-you-go pricing with no monthly fees. Each API call costs credits based on the model and parameters used. Visit the service page for detailed pricing.

Ace Data Cloud

OpenAI Audio Speech API

POSThttps://api.acedata.cloud/v1/audio/speech

POSThttps://api.acedata.cloud/openai/audio/speech

Combine the text into natural speech (OpenAI compatible /v1/audio/speech), supporting multiple voice tones such as tts-1 and tts-1-hd, and directly return audio bytes.

Request Headers

authorizationstring

Bearer token

Request Body

inputstringRequired parameter

Text to be synthesized. Billing is calculated based on the number of requested bytes.

modelstring

Speech synthesis model: tts-1 (faster) or tts-1-hd (higher quality, default).

Please select

speednumber

Speech rate, range 0.25–4.0, default 1.0.

voicestring

Timbre: one of alloy, echo, fable, onyx, nova, shimmer.

Please select

response_formatstring

Audio formats: mp3 (default), opus, aac, flac, wav, or pcm.

Please select

Response

Allow Use General Balance

When 'Allow General Balance' is enabled, the general balance is used automatically if an app's balance is insufficient.

Shell

Python

JavaScript

Java

PHP

Kind reminder: For streaming requests, the above code may not be fully applicable. Please refer to the integration documentation for changes.

Request Headers

Request Body

Response

Response Body

Response Body

Example

Response Body

Example

Response Body

Example

Response Body

Example

Response Body

Example