Play's lifelike voices are fluid, human like (if you prefer), and emotive. Whether you want bloodcurdling screams or yippees, we've got you covered
Trusted by teams at
“With PlayAI expressive and emotional voices, FlipaClip artists can bring original characters to life in no time. This is changing how cartoons are made, giving anyone the power to create high-quality animated films on a mobile device”
Adri Ofman, COO Visual Blasters
Clone speech accurately in as little as ten seconds of recorded speech, use it in any language you like. Build an army of digital talent
Our efficient models and lightning fast inference give you <125ms time to first audio, less if you need our models on-prem
Our TTS makes localizing speech easy -your custom voices carry over to any language, making it a breeze
import * as PlayHT from 'playht';
import fs from 'fs';
// Create a file stream
const fileStream = fs.createWriteStream('turbo-playht.mp3');
// Stream audio from text
const stream = await PlayHT.stream(
'Stream realistic voices that say what you want!',
{
voiceEngine: 'PlayHT2.0-turbo',
voiceId:
's3://voice-cloning-zero-shot/d9ff78ba-d016-47f6-b0ef-dd630f59414e/female-cs/manifest.json',
outputFormat: 'mp3',
}
);
// Pipe stream into file
stream.pipe(fileStream);
Game development is expensive. Our models are efficient, so we keep inference affordable. Call us if you've special requirements
Play's TTS voice models lead the industry in voice quality, prosody and intonation.
Time to first audio as low as 125ms with Play 3.0 mini, less if on-prem deployment required
Voice AI generation and customization all supported by easy to use APIs.
Dialog is fine-tuned to ensure accurate generation of acronyms, numerical sequences (e.g. phone, credit card numbers).
English, Spanish, Arabic fully supported; 25+ languages under development
All models are GDPR, ISO 27001 and SOC 2 type II compliant. On-prem also available.