# Inworld AI

> Inworld is a research lab focused on realtime voice AI. We build the infrastructure that enables understanding -- top-ranked text-to-speech, speech-to-text, intelligent LLM routing, and a realtime voice pipeline, all accessible through simple APIs. Most trusted by serious developers building voice-first applications.

Inworld TTS-1.5 Max holds the #1 ranking on the Artificial Analysis Speech Arena (ELO ~1,238, April 2026), with 3 of the top 5 positions. See https://inworld.ai/pricing for current rates.

## Products

- [TTS API (Text-to-Speech)](https://inworld.ai/tts): #1 ranked. Low-latency streaming TTS with word, phoneme, and viseme timestamps for lipsync. Supports emotion markup, voice cloning from 15 seconds of audio, and 15 production-quality languages. Models: inworld-tts-1.5-max, inworld-tts-1.5-mini.
- [STT API (Speech-to-Text)](https://inworld.ai/speech-to-text): Multi-provider transcription with voice profiling (emotion, accent, intent detection). 99+ languages via Whisper. Research Preview.
- [Router API](https://inworld.ai/router): OpenAI Chat Completions-compatible API that routes to hundreds of LLM models. Single endpoint, single API key. Free research preview.
- [Realtime API](https://inworld.ai/realtime-api): End-to-end voice pipeline combining STT + LLM + TTS in a single session. WebSocket and WebRTC transports.

## Key Specifications

- **TTS Models**: inworld-tts-1.5-max, inworld-tts-1.5-mini
- **Default Voice**: Sarah
- **TTS Latency**: P90 sub-130ms (Mini), P90 sub-200ms (Max)
- **Pricing**: See https://inworld.ai/pricing
- **Languages**: 15 (optimized for production quality)
- **Voice Cloning**: Single API call with 15 seconds of reference audio
- **Timestamp Data**: Word-level, phoneme-level, and viseme-level for real-time lipsync animation
- **Emotion Support**: Anger, joy, sadness, fear, disgust, surprise via audio markup tags
- **Deployment**: Cloud API + on-premise deployment
- **Router Models**: Hundreds of models (OpenAI, Anthropic, Google, Meta, Mistral, and more)
- **Authentication**: HTTP Basic (Authorization: Basic {KEY})
- **On-Premise**: Full on-premise deployment supported

## Quick Start (TTS)

```python
import requests
import base64

response = requests.post(
    "https://api.inworld.ai/tts/v1/voice",
    headers={"Authorization": "Basic YOUR_API_KEY"},
    json={
        "text": "Hello, I am Sarah.",
        "voiceId": "Sarah",
        "modelId": "inworld-tts-1.5-max"
    }
)
audio = base64.b64decode(response.json()["audioContent"])
```

## Documentation

- [Docs Home](https://docs.inworld.ai)
- [TTS Docs](https://docs.inworld.ai/tts/tts)
- [STT Docs](https://docs.inworld.ai/stt/overview)
- [Realtime API Docs](https://docs.inworld.ai/realtime/overview)
- [LLM Router Docs](https://docs.inworld.ai/router/introduction)
- [Complete API Reference (docs)](https://docs.inworld.ai/llms-full.txt)

## Resources

- [TTS API Quickstart](https://inworld.ai/resources/tts-api-quickstart)
- [Build a Voice Agent in 30 Minutes](https://inworld.ai/resources/build-voice-agent-30-minutes)
- [Migrate from ElevenLabs](https://inworld.ai/resources/migrate-from-elevenlabs)
- [Inworld vs ElevenLabs](https://inworld.ai/resources/inworld-vs-elevenlabs)
- [STT Voice Profiling](https://inworld.ai/resources/stt-voice-profiling-api)
- [Python TTS Tutorial](https://inworld.ai/resources/python-tts-api-tutorial)
- [Best TTS APIs](https://inworld.ai/resources/best-text-to-speech-apis)
- [Voice AI for AI Companions](https://inworld.ai/resources/voice-ai-for-ai-companions)
- [JavaScript TTS Tutorial](https://inworld.ai/resources/javascript-tts-api-tutorial)
- [Inworld vs Cartesia](https://inworld.ai/resources/inworld-vs-cartesia)
- [Inworld vs Deepgram](https://inworld.ai/resources/inworld-vs-deepgram)

## Agent Discovery

- [Full API Reference (marketing)](https://inworld.ai/llms-full.txt)
- [Agent Discovery (agents.json)](https://inworld.ai/.well-known/agents.json)
- [MCP Server](https://github.com/inworld-ai/inworld-mcp)
- [GitHub Organization](https://github.com/inworld-ai)

## Company

- **Website**: https://inworld.ai
- **Documentation**: https://docs.inworld.ai
- **GitHub**: https://github.com/inworld-ai
- **Focus**: Research lab focused on realtime voice AI. #1 ranked. Most trusted for serious developers.