Engage every user with the #1 ranked, most natural Voice AI
#1 ranked TTS with human-like expression and realtime sub-200ms latency that feels like a real conversation. Custom voices with instant cloning or text-based voice design. Fully multilingual, built for streaming, and a fraction of the cost of other providers.
One API. Streaming, cloning, voice design.
Stream audio chunks back as the model generates them. Sub-200ms first-chunk latency keeps the conversation feeling natural.
The top ranked TTS in the world. Proven by real users.
3 of the top 5 models on Artificial Analysis are Inworld. Blind tests by thousands of real users, not internal evals. Realtime TTS 1.5 Max delivers over 30% more expressiveness than previous models, with optimized stability to eliminate hallucinations and artifacts.
Clone any voice. Localize to any language.
Create a custom voice from 15 seconds of audio, then localize it to speak over 100 languages as a native speaker — same identity, no accent carryover. Production-ready voices you can use in the Playground or via API.
- Instant cloning: 15 seconds of audio → ready in seconds
- Localize: one voice, native delivery in over 100 languages
Describe any voice. Generate it instantly.
Skip recording entirely. Describe accent, age, tone, and energy in natural language, and Inworld renders a production-ready voice on the fly.
- No audio sample required — pure natural-language description
- Per-preset playback so you can compare styles before generating
Realtime latency. Instant responses.
Built for realtime from the ground up — audio generates the instant it's synthesized via WebSocket. No buffering delay. Comparable latency to competitors at a fraction of the cost.
Direct the voice. Match the moment.
Add bracketed instructions anywhere in your text and Realtime TTS-2 adjusts the utterance. Pair with various non-verbals and adjustable pauses for delivery that matches the moment, not just the words.
Over 100 languages. Native-speaker quality.
English, Spanish, French, Korean, Chinese, Hindi, Japanese, German, and more. Native-speaker quality in every language with cross-lingual cloning. Deploy globally without separate pipelines.
Starting at $15 per million characters.
Realtime TTS 1.5 Mini at $15/million characters. Realtime TTS 1.5 Max and Realtime TTS-2 at $25/million. Comparable providers charge $120/million — Inworld is up to 87% cheaper at scale.
Built for voice-first applications
- Voice Agents
- Audiobooks & Narration
- Gaming NPCs
- Accessibility
- Language Tutoring
- Content Creation
Full breakdown
| Feature | Realtime TTS-2 | Realtime TTS 1.5 Max | Realtime TTS 1.5 Mini |
|---|---|---|---|
| Best for | Most expressive applications | Most applications | Latency-critical applications |
| Pricing | $35/million characters | $25/million characters | $15/million characters |
| P90 latency | <250ms | <250ms | <130ms |
| Quality | Highest expressiveness, native steering | Maximum expressiveness and stability | High expressiveness |
| Multilingual | over 100 languages, cross-lingual (BCP-47) | 15 languages | 15 languages |
FAQs
How do I use text-to-speech? Getting started is simple. You can try Realtime TTS instantly in the TTS Playground.
What's new in Realtime TTS-2? Retime TTS-2 is focused on expressiveness and direct authoring control, including natural-language steering and reliable non-verbals.
Which Realtime TTS 1.5 model should I use? Use Realtime TTS 1.5 Max for most applications, and Mini only if minimal latency is your utmost priority.
Can I control emotion, speed, and other voice characteristics? Yes, various parameters can be customized dictating expressiveness and speed.