Voice Cloning
The most realistic voice cloning
Clone any voice from 5 to 15 seconds of audio. Instant cloning for rapid deployment, professional cloning for maximum fidelity. Every cloned voice runs on Realtime TTS with sub-200ms latency, emotion control, and support for 200+ languages, ready for realtime applications at scale.
Cloning is free. You pay only for the speech you generate.
Original voice
5 sec sample
Cloned voice
Ready in minutessub-200ms latency
Clone any voice, three ways
Instant cloning for rapid deployment and user-generated voices. Professional cloning for maximum fidelity where it matters most.
Instant voice cloning
Create a custom voice from 5 to 15 seconds of audio. Zero-shot, available to all users in the Portal. Upload or record a sample and start generating speech in minutes.
Voice Cloning API
Automate voice creation programmatically. Let your users clone their own voices during onboarding, or batch-create voices for content workflows. JavaScript and Python examples on GitHub.
Professional voice cloning
Fine-tuned from 30+ minutes of clean audio. Recommended for uncommon voice types: children's voices, unique accents, or brand voices where instant cloning may not capture the full characteristics. Available by contacting the Inworld team.
Built for realtime applications
Every cloned voice runs on Realtime TTS with the same production-grade latency, expressiveness, and multilingual support, and drops straight into the Realtime API alongside speech-to-text and LLM routing on one bill.
Production-grade latency
100 ms TTFB first chunk for Realtime TTS-2. 20 ms TTFB for Realtime TTS-2 Flash. Streaming-native over WebSocket. No buffering delay.
Expression and emotion control
Audio markups for emotion ([happy], [sad], [angry]), delivery style ([whispering], [laughing]), and non-verbal vocalizations ([breathe], [cough], [sigh]). SSML break tags for precise silence placement.
200+ languages
English, Spanish, French, Korean, Chinese, Hindi, Japanese, German, and more. Native-speaker quality in every language, with cross-lingual cloning on Realtime TTS-2.
Voice AI down to $0.005/min
Realtime TTS-2 as low as $5 per 1M characters at scale. New pricing cuts rates in half or more for most developers, and your rate keeps falling as you scale. On-prem deployment for enterprises with data sovereignty requirements.
Full breakdown
| Feature | Instant Voice Cloning | Professional Voice Cloning |
|---|---|---|
| Audio required | 5 to 15 seconds | 30+ minutes (5 min minimum, 20+ recommended) |
| Availability | All users via Portal and API | Contact sales |
| Best for | Most applications, rapid prototyping, user-generated cloning | Uncommon voice types, brand voices, maximum fidelity |
| Supported formats | WAV, MP3, WebM (max 4MB) | Contact sales |
| Languages | 200+ languages | 200+ languages |
| Emotion and audio markups | Supported | Supported |
| Timestamp alignment | Word, character, phoneme, viseme | Word, character, phoneme, viseme |
| On-premise deployment | Available (H100/B200) Talk to our team | Available (H100/B200) Talk to our team |
| Zero data retention | Available | Available |
Use cases
Social & Tech
AI Companions and Social Apps
Persistent voice identity across sessions. Your companion sounds the same every time a user comes back.
Education
Language Learning
Clone instructor voices for consistent tutoring experiences across 200+ languages.
Creative
Content Production
Produce podcasts, narration, and video voiceovers in your own voice without being in the booth.
Interactive
Interactive Media
Clone talent and narrator voices for dynamic interactive media. Scale voice production without booking studio time for every line.
Impact
Accessibility
Preserve a person's voice for text-to-speech interfaces. Clone from a short sample and give users a voice that sounds like them.
How Inworld compares
| Inworld | ElevenLabs | Cartesia | |
|---|---|---|---|
| Min audio to clone | 5 seconds | ~60 seconds | 3 seconds |
| Latency (first audio) | 100 ms TTFB (TTS-2), 20 ms TTFB (TTS-2 Flash) | ~300–400ms | ~40ms (base model) |
| Cost per 1M characters | As low as $5 (TTS-2) | $100 (standard) | ~$35† |
| Languages | 200+ (Realtime TTS-2) | 70+ (Eleven v3) | 17 |
| On-premise deployment | ✓ H100/B200 | ✗ | ✗ |
| Zero data retention | ✓ | Enterprise only | ✗ |
| Emotion & audio markups | ✓ | Partial | ✗ |
Inworld latency is P90 time to first audio byte, measured server-side. Cost per 1M characters from provider pricing pages, June 2026. † Cartesia Sonic 3.5 is an estimated effective rate derived from published tier pricing.
FAQ
AI voice cloning creates a digital replica of a specific voice from audio samples. The cloned voice can then generate new speech that sounds like the original speaker. Inworld offers instant voice cloning from 5 to 15 seconds of audio, and professional voice cloning from 30+ minutes for maximum fidelity.
Open the TTS Playground in the Inworld Portal. Click Create Voice, then Clone. Upload or record 5 to 15 seconds of audio. Your cloned voice is ready to use in the Playground or via API within minutes. For automation, use the Voice Cloning API with JavaScript or Python.
Instant cloning: 5 to 15 seconds. Professional cloning: 5 minutes minimum, 20 to 30+ minutes recommended. For instant cloning, record in a quiet environment and speak with varied emotion to capture the full range of the voice.
Yes. You must confirm you have the rights to clone the voice during the creation process.
Cloned voices speak 200+ languages on Realtime TTS-2 and Realtime TTS-2 Flash, with cross-lingual synthesis that keeps the same voice identity across languages. Voices perform best when the synthesized text matches the language of the original sample.
Instant cloning (zero-shot) creates a usable voice from 5 to 15 seconds of audio. Available to all users. Professional cloning fine-tunes a model with 30+ minutes of audio for maximum fidelity. Recommended for uncommon voice types where instant cloning may not capture the full characteristics.
Yes. Automate voice creation programmatically. Useful for onboarding flows where users clone their own voice, or batch workflows. Code examples in JavaScript and Python on GitHub.
Cloning itself is free. You pay only for speech synthesis: Realtime TTS-2 as low as $5 per 1M characters at scale. New pricing cut rates in half or more for most developers, and rates fall further as your volume grows. Full tiers are at inworld.ai/pricing.
Yes. Audio markups for emotion ([happy], [sad], [angry]), delivery style ([whispering], [laughing]), and non-verbal vocalizations ([breathe], [cough], [sigh]). SSML break tags for precise silence. Emotion markups are currently experimental, English only.
Start building
Join millions of developers building the next wave of AI applications.