1from pathlib import Path
2from openai import OpenAI
3
4client = OpenAI(
5    base_url="https://api.AiApiGiaRe.io/v1",
6    api_key=key
7)
8
9speech_file_path = Path(__file__).parent / "speech.mp3"
10response = client.audio.speech.create(
11  model="tts-1",
12  voice="alloy",
13  input="Today is a wonderful day to build something people love!"
14)
15
16response.stream_to_file(speech_file_path)

1from pathlib import Path
2from openai import OpenAI
3
4client = OpenAI(
5    base_url="https://api.AiApiGiaRe.io/v1",
6    api_key=key
7)
8
9speech_file_path = Path(__file__).parent / "speech.mp3"
10response = client.audio.speech.create(
11  model="tts-1",
12  voice="alloy",
13  input="Today is a wonderful day to build something people love!"
14)
15
16response.stream_to_file(speech_file_path)

Overview

The Audio API provides the speech endpoint, powered by TTS models, to achieve the following functionalities:

• 📝 Read blog articles aloud.
• 🌍 Generate multilingual audio.
• 🎵 Output real-time audio streams.

Important Note: You must inform users that the voice they hear is AI-generated and not a human voice.

Basic Usage

Basic Example

(Code extracted to sandbox)

Features

Audio Quality Options

• tts-1: Low latency, suitable for real-time applications.
• tts-1-hd: Higher quality, with potentially fewer static artifacts.

Available Voices

• alloy
• echo
• fable
• nova
• shimmer
• onyx

Supported Output Formats

Real-Time Audio Streaming

(Code extracted to sandbox)

Supported Languages

The API supports multiple languages, including:

• Asian Languages: Chinese, Japanese, Korean, etc.
• European Languages: English, French, German, etc.
• Other Languages: Arabic, Hindi, etc.

Note: The current voices are primarily optimized for English.

Frequently Asked Questions (FAQs)

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

A: There is currently no direct mechanism to control emotions. Capitalization or punctuation might influence the output, but the effect is not guaranteed.

Q: Can I create custom voices?

A: Custom voice creation is not supported at this time.

Q: Who owns the generated audio?

A: The audio belongs to the creator, but you must inform users that the audio is AI-generated.