Skip to main content

openai/tts-1/text-to-speech

OpenAI's TTS-1 is a speech model built for fast, low-latency output: it reads up to 4,096 characters aloud in nine preset voices, with speaking speed adjustable from 0.25× to 4× and MP3, Opus, AAC, FLAC, WAV or PCM files.

From $0.003/1,000 characters80% below the publisher's list price

Workbench

Input

Text to speech
affects price40/4096
Give TTS-1 the exact spoken message, up to 4,096 characters including spaces and punctuation. at least 1 characters · at most 4096 characters

40 characters

Pick a TTS-1 preset from alloy, ash, coral, echo, fable, onyx, nova, sage and shimmer; the default is alloy.
Speed
Set TTS-1 speaking speed between 0.25 and 4; 1 keeps the normal pace. no lower than 0.25 · no higher than 4
Output format
MP3OpusAACFLACWAVPCM (raw)
Choose a TTS-1 file encoding; PCM contains raw 24 kHz, 16-bit little-endian samples without a WAV header.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result
0:00 / –:––

Related models and next tasks

Missing the model you need?

TTS-1 reads short text as speech using nine preset voices, adjustable speaking speed and six audio formats.

Key numbers

Voice presets
9

What it does

Preset voices and six audio formats

A TTS-1 request can use alloy, ash, coral, echo, fable, onyx, nova, sage or shimmer. These preset voices are optimized for English while supporting text in other languages. Keep a chosen voice consistent across related messages, and review important names with a listener who knows the intended language. TTS-1 can produce MP3, Opus, AAC, FLAC, WAV or raw PCM. Compressed output is useful for a spoken notification that must travel over a mobile connection; an uncompressed file fits an application that already controls its audio playback pipeline. Speaking speed is adjustable from 0.25 to 4, but changing speed does not remove words from the submitted message.

Where it fits

  • Audible task-status notifications

    For a task dashboard using TTS-1, turn a completed action into a short audible status message. Have the application decide the status and write the exact words before requesting audio, so the announcement cannot invent an outcome.

  • Spoken device-setup steps

    For a device setup flow, prepare one TTS-1 clip for each instruction or confirmation. Separate clips let the interface play only the relevant step and replace a changed instruction without regenerating the rest of the sequence.

Made with TTS-1

  • Short voice message
  • Speak technical terms
  • Ask a meeting question
  • Departure gate announcement

Model reference

TTS-1 API reference

TTS-1 API specifications

Voice presets
9

How to call the TTS-1 API

  1. Prompt guide & Pro tips

    Write TTS-1 input as the sentence a listener should hear. Expand a product abbreviation when pronunciation matters, and test account codes, dates and decimal numbers in context. A direction such as ‘use a calm voice’ is spoken content here; this legacy model does not offer instruction-based delivery control. Use the voice and speed fields for the available controls. Keep each TTS-1 text within 4,096 characters and each generated file within the platform’s 32 MiB limit. Split long narration into separate messages, especially with slow WAV or PCM output. Check the returned recording before placing it in a user flow, and identify the voice as generated audio in the listening experience. Because the model has an announced retirement date, keep the source text and playback configuration available for migration.

TTS-1 API questions

All TTS-1 models2