TTS-1
Generally availableProprietary
Summary
TTS-1 is a proprietary speech model from OpenAI, released on 6 Nov 2023. It accepts text and generates audio.
Text-to-speech model optimized for low latency
Last verified 21 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | OpenAI |
|---|---|
| Release date | 6 Nov 2023 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Input | Text [models.dev] |
| Output | Audio [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
TTS-1 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Vercel AI Gateway openai/tts-1 | – | – | – | – | models.dev, 21 Oct 2026 |
Frequently asked questions
Is TTS-1 open source?
No. TTS-1 is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.
When was TTS-1 released?
OpenAI released TTS-1 on 6 Nov 2023, according to models.dev.
Change history
- Added to the directory
- Now listed on Vercel AI Gateway