OpenAI TTS

Steerable speech.

GPT-4o-mini-tts generates natural speech with fine-grained control over tone, pace, and style. Streaming supported.

Model
gpt-4o-mini-tts
Voices
6 voices
Languages
50+ languages
Latency
< 500ms
Capabilities

What OpenAI TTS does best

01

Natural speech

Human-like prosody and rhythm with minimal effort.

02

Steerability

Describe the style you want in natural language: 'whisper urgently' or 'speak like a newscaster'.

03

Streaming

Real-time audio output for interactive applications.

04

Expressive

Handles emphasis, pauses, and emotional range naturally.

FAQ

Common questions

What voices are available?

6 built-in voices: alloy, echo, fable, onyx, nova, and shimmer.

What is the maximum input length?

4,096 characters per request. Longer texts are split automatically.

Get started

Ready to try every voice?

Generate, clone, narrate and broadcast from a single workspace. No credit card required to start.