> ## Documentation Index
> Fetch the complete documentation index at: https://docs.geko.sh/llms.txt
> Use this file to discover all available pages before exploring further.

# Roadmap

> What's planned but not yet available.

What exists today is the honest, working surface documented throughout these docs: `tts.create`, **`tts.stream`**, `voices`, `models`, `health`, the **OpenAI-compatible `/v1/audio/speech`** endpoint, and **CORS** for browser callers — with a typed SDK and CLI.

<Warning>
  The items below are **planned, not yet available**. Nothing here is callable today — this page exists so you can plan around it. Track progress on [GitHub](https://github.com/gekoai).
</Warning>

## More output formats

Native **MP3**, **Opus**, and 8 kHz **µ-law** (telephony) alongside WAV/PCM, via the `response_format` parameter — smaller payloads and no client-side transcoding. Until then, [convert with `ffmpeg`](/guides/playing-audio).

*Today the API returns WAV (24 kHz, PCM16); the OpenAI-compatible endpoint also supports raw `pcm`.*

## Python SDK

A `geko` Python package mirroring this SDK's surface (`geko.tts.create(...)`, `geko.tts.stream(...)`), for Python-first backends and agents.

*Today the official SDK is TypeScript/JavaScript (`@gekoai/sdk`).*

## Word / character timestamps

Optional alignment data for captions, subtitles, and highlight-as-it-speaks UIs.

## More languages & voices

Tokay is Kazakh today. New languages and voices appear on the same endpoints — `GET /v1/models` and `GET /v1/voices` are the source of truth, so code that reads them adapts automatically.

***

<Note>
  Want one of these sooner, or have a use case that needs it? Open an issue on [GitHub](https://github.com/gekoai) — it genuinely helps prioritize.
</Note>