# Step TTS 2

`step-tts-2` — **stepfun** · SPEECH

> Step TTS 2 (step-tts-2) is a speech model from stepfun; proprietary (API-only); input text; output audio.

| Field | Value |
| --- | --- |
| Vendor | stepfun |
| Kind | SPEECH |
| Input modalities | text |
| Output modalities | audio |
| Weights | Proprietary (API-only) |
| Release date | 2026-03-01 |
| Sources | models-dev |
| Last verified | 2026-10-30 |

*Part of the [Model Catalog](https://openviglet.github.io/model-catalog/) — [stepfun models](https://openviglet.github.io/model-catalog/models/stepfun/) · [Vendor JSON](https://openviglet.github.io/model-catalog/by-vendor/stepfun.json) · [HTML](https://openviglet.github.io/model-catalog/models/stepfun/step-tts-2.html)*