English

Português

English

Português

Appearance

Text-to-Speech Playground ​

The SipPulse AI text-to-speech playground allows you to test and compare the performance of voice synthesis models available on the platform. This interactive environment facilitates the conversion of text into audio, supporting multiple languages, voices, and output formats.

Key Features ​

Parameter Settings ​

When selecting a model, the playground displays the available parameters for adjustment. These parameters may include:

  • Model: Choose from the available voice synthesis models on the platform.
  • Language: Select the language for the synthesized speech. The model will adjust the voice and pronunciation according to the chosen language.
  • Voice: Choose from different voices available for the selected language. Each voice may have distinct characteristics, such as gender and tone.
  • Output Format: Choose the desired audio format. The main supported formats are:
    • MP3: Compressed audio with good quality and reduced file size.
    • WAV: Uncompressed audio with high quality.
    • Opus: Free and open audio format, compressed, ideal for voice transmissions.
    • PCM: Uncompressed audio with various available sampling rates.
    • MULaw and ALaw: Audio formats used in telecommunications.
    • WebM: Free and open audio format, based on Opus.
    • AMR-WB: Format used in mobile communications.

Text ​

Enter the text you want to convert into speech in the provided text area. The voice synthesis model will use this text to generate the corresponding audio.

Test Execution ​

After adjusting the parameters and entering the text, you can start the test by clicking the Execute button. The model will process the text and generate the audio in the selected format.

Audio Playback ​

After the test execution and audio generation, an audio player will be displayed in the interface, allowing you to listen to the result directly in the playground.

Code Visualization ​

The playground includes a View Code button, which shows how to integrate the tested model and parameters into your own applications. The integration code can be viewed in different languages, including Curl, Python, and JavaScript.

Usage Example ​

Let's suppose you want to convert text into audio using the azure-tts model with a specific configuration:

  1. Select azure-tts from the model menu.
  2. Adjust the Parameters:
    • Language: English (US)
    • Voice: Jenny
    • Output Format: MP3 (16Khz, 64KBit Rate, Mono)
  3. Enter the Text: Type or paste the text you want to convert into speech.
  4. Execute the Test: Click Execute to generate the audio from the entered text.
  5. Listen to the Result: Use the displayed audio player to listen to the conversion result.
  6. View Code: Get the integration code by clicking View Code and choose your preferred language (Curl, Python, or JavaScript).