What is text to speech
Text-to-speech turns written text into natural spoken audio. Here is the plain definition.
Definition
Text-to-speech (TTS) is technology that converts written text into spoken audio. You give it text; it gives you a voice reading that text. Modern TTS uses AI models to produce natural-sounding speech, so the result sounds like a person rather than the flat, robotic voices of older systems.
In practice it is an API call. You send text, choose a voice and language, and receive either an audio file or a live stream of audio. The quality difference between old and new TTS is the naturalness of the voice and the control you have over how it reads.
How it works
An AI model maps your text to a waveform that sounds like a human speaking it. You pick a compatible voice from a catalog of 900+. Simba 3.5 speaks 48 languages under one model id, and the older Simba 3.2 (English) and Simba 3.0 (6 languages) remain available. SSML markup lets you control pauses, speaking rate, and pronunciation. Streaming mode sends audio as it generates, so real-time apps can begin playback before the full clip has rendered.
What it’s used for
TTS powers audiobook and podcast narration, e-learning voiceover, IVR and phone prompts, accessibility read-aloud, video voiceover, game dialogue, and spoken notifications. The common thread is text that needs to be heard: TTS supplies the voice without a studio or a booked voice actor.
How it’s priced
TTS is typically billed per character of input text, which makes cost predictable and scales cleanly from a single notification to a full audiobook. See the pricing page for current rates.
Frequently asked questions
What is text-to-speech?
How does text-to-speech work?
What is text-to-speech used for?
Continue exploring speech.
Start building
Text-to-speech turns written text into natural spoken audio. Here is the plain definition.