> 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

# Guides

## Docs

- [SpeechifyAI Build](https://docs.speechify.ai/build/guides/welcome.md): Generate speech, stream long-form audio, clone a voice, and control delivery with SSML. Quickstarts for Python and TypeScript, plus a full reference.
- [Quickstart](https://docs.speechify.ai/build/guides/get-started/quickstart.md): Make your first SpeechifyAI Build TTS call: get an API key, install the Python or TypeScript SDK, generate speech, and choose a voice.
- [Text-to-Speech Quickstart](https://docs.speechify.ai/build/text-to-speech-quickstart.md): Text-to-speech quickstart: get an API key, install the SDK, call POST /v1/audio/speech, and save a playable audio file in a few minutes.
- [Text-to-Speech API](https://docs.speechify.ai/build/text-to-speech-api.md): The SpeechifyAI text-to-speech API: authenticate, call POST /v1/audio/speech with the Python, TypeScript, or HTTP SDK, and get natural audio back fast.
- [Streaming TTS Guide](https://docs.speechify.ai/build/streaming-tts-guide.md): Streaming text-to-speech guide: call POST /v1/audio/stream to receive audio chunks in real time, begin playback early, and handle up to 20,000 characters.
- [Voice Cloning Quickstart](https://docs.speechify.ai/build/voice-cloning-quickstart.md): Voice cloning quickstart: record a short sample, have the speaker read a consent phrase, POST both to /v1/voices, and synthesize speech in the cloned voice. Verified consent is required.
- [Authentication](https://docs.speechify.ai/build/guides/get-started/authentication.md): Authenticate Speechify API requests with a Bearer API key. Get and rotate keys in the console, store them securely, and use a server-side proxy for frontends.
- [Service accounts](https://docs.speechify.ai/build/guides/get-started/service-accounts.md): Service accounts are machine identities that hold a scope ceiling and own one or more API keys. Rotate keys with zero downtime and mint short-lived, least-privilege keys for agents.
- [Enterprise SSO](https://docs.speechify.ai/build/guides/get-started/enterprise-sso.md): Set up enterprise SAML or OIDC single sign-on for a Speechify workspace through the WorkOS Admin Portal. Owners and admins connect an identity provider once; members then sign in with their work email.
- [Official SDKs](https://docs.speechify.ai/build/guides/get-started/official-sdks.md): Install and use the official Speechify API SDKs for Python and TypeScript, or call the REST API directly. Both SDKs read SPEECHIFY_API_KEY automatically.
- [Connect the docs MCP server](https://docs.speechify.ai/build/guides/get-started/connect-mcp.md): Install the Speechify docs MCP server (https://docs.speechify.ai/_mcp/server) in Claude Code, Cursor, VS Code, Windsurf, or Claude Desktop. It answers questions about the Speechify API, SDKs, and docs with citations to the page it found.
- [Testing Safely](https://docs.speechify.ai/build/guides/get-started/testing-safely.md): Test the Speechify API safely without a sandbox: create a dedicated development workspace, fund a prepaid balance, and cap what a test key may spend.
- [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.
- [Voice Cloning](https://docs.speechify.ai/build/guides/voice-cloning/overview.md): Clone a voice you have consent for from a 10-30 second sample with the Speechify API: capture verified consent, create the voice, use it in any speech request, and delete it when done.
- [Consent](https://docs.speechify.ai/build/guides/voice-cloning/consent.md): Voice cloning consent explained: create a consent challenge, have the speaker read the issued phrase aloud, and pass the recording with the create call. Covers the challenge lifecycle, recording rules, verification failures, and rate limits.
- [Voice Cloning API](https://docs.speechify.ai/build/voice-cloning-api.md): Voice cloning API guide: create a consent challenge, record the speaker reading it, POST both to /v1/voices, and synthesize speech in the cloned voice. Verified consent is required.
- [Manage Voices](https://docs.speechify.ai/build/guides/voice-cloning/manage.md): Manage cloned voices on the Speechify API: list voices alongside the catalog, get one by id, download its sample as WAV, and delete voices you no longer need.
- [Integrations](https://docs.speechify.ai/build/guides/integrations.md): Integration guides for using SpeechifyAI Build with the Vercel AI SDK, LiveKit, Pipecat, Vapi Voice Agent, and Deepgram Voice Agent.
- [LiveKit](https://docs.speechify.ai/build/guides/integrations/livekit.md): Use LiveKit's official Speechify plugins, `livekit-plugins-speechify` for Python and `@livekit/agents-plugin-speechify` for Node.js, to add Speechify text-to-speech to a LiveKit voice agent.
- [Pipecat](https://docs.speechify.ai/build/guides/integrations/pipecat.md): Use Pipecat's built-in SpeechifyHttpTTSService (pipecat-ai 1.8.0 and later) to add Speechify text-to-speech, with word-level timestamps, to a Pipecat voice agent.
- [Vercel AI SDK](https://docs.speechify.ai/build/guides/integrations/vercel-ai-sdk.md): Use @speechify/ai-sdk-provider, the Speechify-maintained provider for the Vercel AI SDK, to call Speechify text to speech from generateSpeech() with word-level speech marks.
- [Vapi](https://docs.speechify.ai/build/guides/integrations/vapi.md): Use the tts-shims Vapi provider to answer Vapi's custom TTS voice-request with raw PCM from Speechify while keeping your API key server-side.
- [Deepgram](https://docs.speechify.ai/build/guides/integrations/deepgram.md): Give Deepgram Voice Agent a Speechify voice via the tts-shims openai binary. The shim answers Deepgram's open_ai TTS request and keeps your Speechify key server-side.
- [Puter](https://docs.speechify.ai/build/guides/integrations/puter.md): Use the Speechify TTS provider in Puter's puter.js SDK: on puter.com with no API key, or on your own Puter instance with your key.
- [Build an integration](https://docs.speechify.ai/build/guides/integrations/build-an-integration.md): How to build a Speechify TTS integration: set the Speechify-Caller header, choose a slug, and understand what Speechify does with it.
- [API Versioning](https://docs.speechify.ai/build/guides/concepts/api-versioning.md): How Speechify API date-based versioning works, including the Speechify-Version header, workspace defaults, and deprecation windows.
- [Models](https://docs.speechify.ai/build/guides/concepts/models.md): Compare Speechify's streaming-native TTS models. Simba 3.2 is recommended for English; Simba 3.0 is the API default with six languages across seven locales. Both support voice cloning on paid plans.
- [Audio formats](https://docs.speechify.ai/build/guides/concepts/audio-formats.md): The two parameters that decide what bytes come back, and which one wins.
- [API Limits](https://docs.speechify.ai/build/guides/concepts/api-limits.md): Speechify API rate limits and concurrency limits by plan (Free through Enterprise), plus per-endpoint character limits. Every /v1/audio synthesis endpoint shares one per-account rate and concurrency budget. Includes 429 Too Many Requests handling with Retry-After, rate_limited, and concurrency_limit_reached.
- [Spend Limits](https://docs.speechify.ai/build/guides/concepts/spend-limits.md): Set a monthly USD spend limit on any Speechify API key. Requests are refused with 402 spend_cap_exceeded once the key reaches its limit; the limit resets each calendar month.
- [Projects](https://docs.speechify.ai/build/guides/concepts/projects.md): How Speechify projects work: what a project groups, how a project grant scopes a member, what archive and delete do, and what projects do and do not scope in SpeechifyAI Build.
- [Error Handling and Retries](https://docs.speechify.ai/build/guides/concepts/error-handling.md): Handle Speechify API errors correctly: retry 429, 502, 503, and 504 with exponential backoff; fix 4xx client errors; log the request id.
- [Content Policy](https://docs.speechify.ai/build/guides/concepts/content-policy.md): Speechify screens the text you send for synthesis. A request refused under the content policy returns 400 content_policy_violation or, on a stream already playing, ends early, and is not billed.
- [Safety Identifiers](https://docs.speechify.ai/build/guides/concepts/safety-identifiers.md): Send safety_identifier on Speechify TTS requests to attribute each one to an end user of your application. Abuse can then be limited or blocked for that one user instead of your whole workspace. Send a hash, never an email address.
- [Migrating off Simba 1.6](https://docs.speechify.ai/build/migrating-off-simba-1-6.md): The Simba 1.6 text-to-speech models simba-english and simba-multilingual retire at API version 2026-09-21, and from 2026-11-21 both ids are served by current Speechify models. This guide shows what changes, which model to move to, checking your languages first, and how to pin your API version to keep Simba 1.6 until then.
- [Migrating to verified voice-cloning consent](https://docs.speechify.ai/build/migrating-voice-cloning-consent.md): The old voice-cloning consent form field (fullName + email) was switched off on 2026-09-23. This guide moves you to verified consent: create a consent challenge, record the speaker reading the phrase, and send consent_challenge_id + consent_recording to POST /v1/voices. Re-pin Speechify-Version 2026-09-13.