LLM Reference

OpenAI Text-to-Speech Models by OpenAI

OpenAIProprietaryAudio
4 models2023–2025Up to 2k ctxFrom $0.6/1M input

Last refreshed 2026-06-07. Next refresh: weekly.

Details

ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models4
Released2023–2025
Max context2k

Capabilities

Multimodal1 of 4 models

Links

Website

About

OpenAI's text-to-speech family includes the legacy TTS endpoints and the newer GPT-4o mini TTS model for controllable, low-latency speech generation.

Decision facts

Best fit
audiotext to speechvision and multimodal work
Capability starting point
GPT-4o Mini TTS with 2k context and multimodal inputs
Lowest tracked input
GPT-4o Mini TTS · $0.6/1M · OpenAI API
Closest related family
GPT Realtime 2

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

4 in view

Use when the workload needs audio, 2k context, and multimodal inputs.

2025-03audio2k contextmultimodal inputs
TTS-1Current

Use when the workload needs audio.

2023-11audio
TTS-1 HDCurrent

Use when the workload needs audio.

2023-11audio
OpenAI TTSCurrent

Use when the workload needs text to speech and audio.

2023-11text to speechaudio

Release Timeline

2 release groups
2025-03
1 current
GPT-4o Mini TTS
audio2k contextmultimodal inputs
Current
2023-11
3 current
OpenAI TTS
text to speechaudio
Current
TTS-1
audio
Current
Current

Specifications(4 models)

OpenAI Text-to-Speech model specifications comparison
ModelReleasedContextMultimodal
GPT-4o Mini TTS2025-032kYes
TTS-12023-11No
TTS-1 HD2023-11No
OpenAI TTS2023-11No

Available From(1 provider)

Pricing

OpenAI Text-to-Speech model pricing by provider
ModelProviderInput / 1MOutput / 1MType
GPT-4o Mini TTSOpenAI API$0.6Serverless
TTS-1OpenAI API$15Serverless
TTS-1 HDOpenAI API$30Serverless