Text-to-Speech (TTS) API Guide

Overview

The Audio API provides a speech endpoint, based on the TTS model, to implement the following features:

📝 Blog article reading

🌍 Multilingual audio generation

🎵 Real-time audio stream output

Important Note: You must clearly state to users that what they hear is AI-generated speech, not a human voice

Basic Usage

Basic Example

Features

Audio Quality Options

tts-1: Low latency, suitable for real-time applications

tts-1-hd: Higher quality, may have less static

Available Voices

alloy

echo

fable

nova

shimmer

onyx

Supported Output Formats

Format	Features	Use Cases
MP3	Default format	General scenarios
Opus	Low latency	Web streaming and communications
AAC	Efficient compression	Mobile device playback
FLAC	Lossless compression	Audio archiving
WAV	Uncompressed	Low-latency applications
PCM	Raw sampling	24kHz, 16-bit signed

Real-time Audio Streaming

Supported Languages

Supports multiple languages, including:

Asian languages: Chinese, Japanese, Korean, etc.

European languages: English, French, German, etc.

Other languages: Arabic, Hindi, etc.

Note: Current voices are mainly optimized for English

FAQ

Q: How can I control the emotion of the generated audio?

A: There is currently no direct control mechanism. Uppercase letters or grammar may affect the output, but the effect is uncertain.

Q: Can I create custom voices?

A: Creating custom voices is not supported.

Q: Who owns the generated audio?

A: It belongs to the creator, but users must be informed that this is AI-generated audio.

python using text-to-speech

Text-to-Speech (TTS) API Guide#

Overview#

Basic Usage#

Basic Example#

Features#

Audio Quality Options#

Available Voices#

Supported Output Formats#

Real-time Audio Streaming#

Supported Languages#

FAQ#

Q: How can I control the emotion of the generated audio?#

Q: Can I create custom voices?#

Q: Who owns the generated audio?#