# SpeechifyAI API > Build speech into your product with one API. Generate audio, stream long-form text, clone voices, and control delivery with SSML. ## Instructions for AI Agents - For clean Markdown of any page, append `.md` to the page URL - For the full page index, append `/llms.txt` to the product URL: https://docs.speechify.ai/build/llms.txt lists every page - Ask, don't scrape. These docs ship with an MCP server that 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.md 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://eu.api.speechify.ai, https://us.api.speechify.ai: the same API with synthesis pinned to Europe or US East. Not data residency: account data, keys, voices and logs stay in the US. https://docs.speechify.ai/build/guides/get-started/regions.md - 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. `SimbaVoice` / `simbavoice.ai` are retired. ## Writing code against this API Model ids for the `model` field: - `simba-3.5`: 48 languages under one model id, English included (set `language`). The recommended model. - `simba-3.2`: English. - `simba-3.0`: English, German, Spanish, French, Italian and Portuguese (set `language`). The default when `model` is omitted. - `simba-english` and `simba-multilingual` (Simba 1.6) are retired. A new workspace that sends either gets `400 model_retired`. Use `simba-3.5` for new code. `GET /v1/audio/models` returns the ids your workspace can use today, with the languages each one covers. This is not the ElevenLabs or OpenAI request shape. Authenticate with `Authorization: Bearer ` (not `xi-api-key`), send the text as `input` (not `text`), and the model as `model` (not `model_id`). There is no `voice_settings` object. Set `language` (for example `fr-FR`) to the language of the input text when it differs from the voice's locale. When `language` is omitted, the API uses the voice's locale. A request that works as written: ```bash curl -X POST https://api.speechify.ai/v1/audio/speech \ -H "Authorization: Bearer $SPEECHIFY_API_KEY" \ -H "Content-Type: application/json" \ -d '{"input": "Hello from Speechify.", "voice_id": "geffen_32", "model": "simba-3.5", "audio_format": "mp3"}' ``` The response is JSON with the audio base64-encoded in `audio_data`. For playback while it generates, `POST /v1/audio/stream` with the same body returns raw audio bytes (`Accept: audio/mpeg`). ## Products - [Build](https://docs.speechify.ai/build/llms.txt): text-to-speech, streaming, voice cloning, SSML - [Welcome](https://docs.speechify.ai/build/guides/welcome.md) - [Text-to-Speech Quickstart](https://docs.speechify.ai/build/text-to-speech-quickstart.md) - [Text-to-Speech API](https://docs.speechify.ai/build/text-to-speech-api.md) - [Streaming TTS Guide](https://docs.speechify.ai/build/streaming-tts-guide.md) - [Latency](https://docs.speechify.ai/build/guides/text-to-speech/latency.md) - [Voice Cloning Quickstart](https://docs.speechify.ai/build/voice-cloning-quickstart.md) - [Connect the docs MCP server](https://docs.speechify.ai/build/guides/get-started/connect-mcp.md)