> This page is for Build.

> 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-3.5` (48 languages under one id, English included; recommended), `simba-3.2` (English) 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

# API: Simba 3.5 takes `pronunciations` in English

`pronunciations` now works on English requests to Simba 3.5 (`simba-3.5`), on `POST /v1/audio/speech`, `POST /v1/audio/stream`, `POST /v1/audio/stream/with-timestamps` and the `GET /v1/audio/stream/ws` input stream.
Until today an English request with the field returned `400 pronunciations_unsupported`.

- **English has its own phone set.** An English request's `ipa` phones are checked against the 110 phones its English model reads, and every other language keeps the set it uses today. The [phone set](/build/guides/text-to-speech/pronunciation#the-phone-set) lists both.
- **A phone outside the set is refused before anything is synthesized or billed**, with `400 validation_failed` naming the entry, and the message names the language when Simba 3.5 reads that phone in another one.
- **`GET /v1/audio/models` lists `en` in Simba 3.5's `pronunciation_languages`.**
- **`alias` entries work the same in English** as in every other language.

Nothing changes for a request without `pronunciations`, and no API version change is needed.
The [pronunciation guide](/build/guides/text-to-speech/pronunciation) has an English example.