# Iodine

> Lifelike text-to-speech API. POST text to https://api.iodine.dev/v1/tts and get 24 kHz audio back, streamed while it's generated; or speak an LLM's reply as it's written over the realtime WebSocket. Pay as you go at $0.0075 per minute of audio.

Everything in one file: https://docs.iodine.dev/llms-full.txt (Markdown) or https://docs.iodine.dev/all (HTML).

## Docs

- [Introduction](https://docs.iodine.dev/): Lifelike speech from text, streamed back while it's generated. Make your first request in a minute.
- [Text to speech](https://docs.iodine.dev/text-to-speech): POST /v1/tts. Send text, get audio back, streamed as it's generated.
- [Emotion and delivery](https://docs.iodine.dev/directions): Direct a v2 voice like an actor. Cues in curly braces set the emotion, add sounds and pauses, and change how words are said.
- [Realtime](https://docs.iodine.dev/realtime): One WebSocket for voice agents. Send text as your LLM writes it; speech starts after the first sentence.
- [Voices](https://docs.iodine.dev/voices): List the voices you can use, and clone a voice from a short recording.
- [Speech to text](https://docs.iodine.dev/speech-to-text): POST /v1/stt. Send a recording, get the words back. Works with OpenAI's SDKs too.
- [Errors and limits](https://docs.iodine.dev/errors): Every error is JSON with a stable code. What each one means and what to do about it.
- [Billing and data](https://docs.iodine.dev/billing): Prepaid credit, priced per minute of audio. Zero Data Retention is on by default.