RailwailRailwail

OpenAI TTS-1

OpenAI
Text-to-Speech

OpenAI's text-to-speech model. Six built-in voices with natural intonation.

Speak with OpenAI TTS-1
Type any text and hear it spoken in a chosen voice.
Sign in to try this model with €5 free credits.
Sign in
Audio player appears here.
TL;DR·Last updated March 4, 2026

OpenAI TTS-1 is text-to-speech AI model from OpenAI, priced at €0.000 per 1M input tokens with a unknown context window.

Try OpenAI TTS-1

1x

Sign in to generate — 50 free credits on sign-up

Examples

See what OpenAI TTS-1 can generate

Notification Voice

Input text:

"Your order has been confirmed and is being prepared. Estimated delivery time is thirty-five minutes. You'll receive a notification when your driver is on the way."

0:04

Tutorial Guide

Input text:

"Step one: open your terminal and navigate to the project directory. Step two: run npm install to download all dependencies. Step three: create a dot env file and add your API keys. Finally, run npm run dev to start the development server."

0:04

Pricing

Price per Generation
Per generation€0.60

API Integration

Use our OpenAI-compatible API to integrate OpenAI TTS-1 into your application.

Install
npm install railwail
JavaScript / TypeScript
import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

// Simple — just pass a string
const reply = await rw.run("openai-tts-1", "Hello! What can you do?");
console.log(reply);

// With message history
const reply2 = await rw.run("openai-tts-1", [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);

// Full response with usage info
const res = await rw.chat("openai-tts-1", [
  { role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);
Specifications
Price
€0.60
Avg. latency
2.0s
Est. duration
2s
Developer
OpenAI
Category
Text-to-Speech
Supported Formats
mp3
opus
aac
flac
Tags
fast
affordable

Deep dive — OpenAI's OpenAI TTS-1

About OpenAI
Founded 2015 · San Francisco, California, USA

OpenAI was founded in December 2015 by Sam Altman, Elon Musk, Greg Brockman, Ilya Sutskever, Wojciech Zaremba and John Schulman as a non-profit AI research lab. It restructured into the capped-profit OpenAI LP in 2019 and has since received over $13B from Microsoft plus billions more from Thrive Capital, Sequoia, Khosla and SoftBank, at a 2024 valuation north of $157B and a planned 2025 round reportedly at $500B. The audio research line at OpenAI includes Jukebox (2020), Whisper (2022) and the TTS-1 family released in November 2023 alongside the ChatGPT voice feature. TTS-1 powers ChatGPT Voice Mode, the OpenAI API audio endpoint and the Realtime API used in voice agents.

Visit OpenAI →
Architecture
Proprietary Transformer text-to-speech with neural codec

OpenAI TTS-1 is the standard-quality variant of OpenAI's text-to-speech model family, optimised for real-time streaming inside ChatGPT Voice and the Realtime API. It is a Transformer-based model that predicts neural-codec audio tokens conditioned on text and a fixed set of stock voices (alloy, echo, fable, onyx, nova, shimmer) that OpenAI recorded with professional voice talent. There is no voice cloning. The model supports six output formats (MP3, Opus, AAC, FLAC, WAV, PCM) and outputs at 24 kHz. TTS-1 is tuned for low latency and starts streaming audio within a few hundred milliseconds, making it suitable for live conversational agents, while the HD sibling trades latency for fidelity. Text input is capped at 4,096 characters per request. OpenAI has not published a technical paper but the system architecturally resembles published neural-codec TTS such as VALL-E.

Parameters
Undisclosed
Context
4.1K tokens
What it can do
  • Real-time streaming TTS with sub-second first-byte latency
  • Six recorded voices: alloy, echo, fable, onyx, nova, shimmer
  • Multilingual: 50+ languages including English, German, Spanish, French, Italian, Japanese, Mandarin
  • Six output formats including streaming PCM for low latency
  • Powers ChatGPT Voice and the OpenAI Realtime API
  • Inexpensive at $0.015 per 1,000 characters (vs. $0.03 for HD)
  • Best for: voice agents, IVR, interactive narration, accessibility
Training & License

Not disclosed. OpenAI states voices were recorded with paid professional voice actors and the model was trained on a mixture of recorded speech and licensed text-audio pairs.

License: Proprietary commercial API. Generated audio may be used commercially under the OpenAI Usage Policy; the six stock voices cannot be impersonated outside the API.

Known limitations
  • No custom voice cloning
  • Limited prosody / emotion control
  • Quality below TTS-1 HD on slow, emotional narration
  • Hard cap of 4,096 characters per request
  • Closed weights, hosted only

Research papers

Frequently asked questions

Related Models

View all Text-to-Speech

ElevenLabs Multilingual V2

ElevenLabs

ElevenLabs' most natural-sounding TTS model. Supports 29 languages with emotional range.

€1.00

AudioCraft

Replicate

Meta's AudioCraft framework wrapping MusicGen, AudioGen and EnCodec. Unified text-to-audio research toolkit for music and sound effects.

€0.01

AudioLDM 2

AudioLDM

Latent-diffusion model for general-purpose text-to-audio. Generates speech, music, and sound effects with a unified prior.

€0.01

Cartesia Sonic

Custom

Cartesia's ultra-low-latency TTS (~90ms TTFB). State-space model with voice cloning support.

Free

Start using OpenAI TTS-1 today

Get started with free credits. No credit card required. Access OpenAI TTS-1 and 100+ other models through a single API.

Get Started FreeBrowse All Models