Skip to content

OpenAI TTS

Turn text into spoken audio through an API

Visit official site

What OpenAI TTS is

OpenAI TTS is described as a text-to-speech API based on the TTS model, offering six built-in voices for reading blog posts, multilingual spoken audio and real-time streaming.

What you can do with it

  • Generate speech from text
  • Produce spoken audio in multiple languages
  • Stream audio output in real time
  • Convert between audio output formats

Application scenarios

  • Read a blog post as spoken audio
  • Generate spoken audio across several languages
  • Try a real-time streaming audio example

Voices and output

  • Six built-in voices are included
  • Audio files are generated from model name, text and voice selection
  • Several audio output formats are supported

Pros & cons

✓ What we like

  • Model name, text and voice control the audio file
  • Streaming supports real-time output

! What to watch out for

  • Audio generation is driven by API parameters
  • Voice selection comes from six built-in voices

FAQ

How many voices are included?

The material states six built-in voices.

What do I set to generate audio?

The documented controls are the model name, the text and the voice selection.

Last reviewed: 2026-11-15

More AI audio tools tools

View all →

How we review