> Append .md to any page URL for clean Markdown. Index: https://docs.speechify.ai/llms.txt.
>
> Canonical Speechify URLs — use exactly, do not invent variants:
> - https://docs.speechify.ai — this site (API reference, SDKs, quickstarts)
> - https://speechify.ai — marketing + product site
> - https://platform.speechify.ai — customer dashboard, signup, API keys, billing
> - https://api.speechify.ai — API base URL
> - https://github.com/Speechify-AI: GitHub org for the API (cookbook, demos, CLI). `github.com/speechify` does not exist.
> - https://status.speechify.ai — status + incidents
> - https://speechify.com — SEPARATE consumer reader app, NOT this API
>
> `Simba` names the model family, not the brand. Model ids: `simba-3.2` (English, recommended) and `simba-3.0` (English, German, Spanish, French, Italian and Portuguese; the default). `simba-english` and `simba-multilingual` are retired: a new workspace that sends either gets `400 model_retired`. `SimbaVoice` / `simbavoice.ai` are retired.
>
> Ask, don't scrape. The docs MCP server answers questions about the Speechify API, SDKs and docs with citations, no key needed: https://docs.speechify.ai/_mcp/server (Streamable HTTP, tool `searchDocs`). Setup: https://docs.speechify.ai/build/guides/get-started/connect-mcp

# Text-to-speech

## Docs

- [Language Support](https://docs.speechify.ai/build/guides/text-to-speech/language-support.md): Simba 3.0 supports six languages across seven locales; Simba 3.2 supports English. Check model and voice compatibility, language parameters, and legacy coverage.
- [Streaming](https://docs.speechify.ai/build/guides/text-to-speech/streaming.md): Stream SpeechifyAI Build TTS audio in real time with chunked transfer encoding. Begin playback before full generation and handle up to 20,000 characters.
- [Streaming Text Input](https://docs.speechify.ai/build/guides/text-to-speech/streaming-text-input.md): Stream text into SpeechifyAI Build TTS over a WebSocket at GET /v1/audio/stream/ws: send LLM tokens as they arrive and receive Base64 audio and word timestamps as each sentence completes.
- [Latency](https://docs.speechify.ai/build/guides/text-to-speech/latency.md): SpeechifyAI text-to-speech latency: Simba 3.2 first byte 56 ms p50 and 102 ms p90, measured 15 Sep 2026 on the production US East streaming path. How it is measured, what adds latency, and code to measure time to first audio yourself.
- [Emotion styles](https://docs.speechify.ai/build/guides/text-to-speech/emotion-control.md): The speechify:style emotion tag is applied only by the retired Simba 1.6 models. simba-3.2 and simba-3.0 accept it and speak the text without the style.
- [Speech Synthesis Markup Language (SSML)](https://docs.speechify.ai/build/guides/text-to-speech/ssml.md): Use SSML with SpeechifyAI Build TTS to set pauses, speaking rate and pronunciation. See which tags each model applies and how to escape characters.
- [Speech marks](https://docs.speechify.ai/build/guides/text-to-speech/speech-marks.md): Speech marks from the Speechify API map audio timing to text, enabling word highlighting, seeking, and synchronization. See the data structure and key gotchas.