XTTS
Generate speech from text with voice cloning using XTTS v2. Supports 16 languages and custom speaker voices for natural-sounding text-to-speech synthesis.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "xtts-v2",
"version": "0.0.1",
"input": {
"text": "Welcome to our platform. We are excited to have you here today.",
"language": "en",
"cleanup_voice": true
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
| cleanup_voice |
boolean |
true |
Refine and improve the quality of generated speech |
| language |
string |
en |
Language for synthesis. enum: en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh, hu, ko, hi |
| speaker |
string |
- |
Specific voice/persona to speak the text |
| text |
string |
Hello, you are now at Eachlabs AI... |
Written input to convert into spoken words |
Examples
Spanish voice synthesis:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "xtts-v2",
"version": "0.0.1",
"input": {
"text": "Bienvenidos a nuestra plataforma de inteligencia artificial. Estamos encantados de tenerte aqui.",
"language": "es",
"cleanup_voice": true
}
}'
Custom speaker voice cloning:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "xtts-v2",
"version": "0.0.1",
"input": {
"text": "This is a demonstration of voice cloning technology with natural-sounding speech output.",
"speaker": "https://example.com/voice-sample.wav",
"language": "en",
"cleanup_voice": true
}
}'
Related Models
Documentation
1---2name: xtts-v23description: XTTS | Text-to-Speech with Voice Cloning. Generate speech from text with voice cloning in 16 languages. Triggers: xtts, text to speech, tts, voice cloning, speech synthesis4---56# XTTS78Generate speech from text with voice cloning using XTTS v2. Supports 16 languages and custom speaker voices for natural-sounding text-to-speech synthesis.910## Quick Start1112> Requires an each::labs API key. Get one at [eachlabs.ai](https://eachlabs.ai).1314```bash15curl -X POST https://api.eachlabs.ai/v1/prediction \16 -H "Content-Type: application/json" \17 -H "X-API-Key: $EACHLABS_API_KEY" \18 -d '{19 "model": "xtts-v2",20 "version": "0.0.1",21 "input": {22 "text": "Welcome to our platform. We are excited to have you here today.",23 "language": "en",24 "cleanup_voice": true25 }26 }'27```2829## Parameters3031| Parameter | Type | Default | Description |32|-----------|------|---------|-------------|33| cleanup_voice | boolean | true | Refine and improve the quality of generated speech |34| language | string | en | Language for synthesis. enum: en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh, hu, ko, hi |35| speaker | string | - | Specific voice/persona to speak the text |36| text | string | Hello, you are now at Eachlabs AI... | Written input to convert into spoken words |3738## Examples3940**Spanish voice synthesis:**41```bash42curl -X POST https://api.eachlabs.ai/v1/prediction \43 -H "Content-Type: application/json" \44 -H "X-API-Key: $EACHLABS_API_KEY" \45 -d '{46 "model": "xtts-v2",47 "version": "0.0.1",48 "input": {49 "text": "Bienvenidos a nuestra plataforma de inteligencia artificial. Estamos encantados de tenerte aqui.",50 "language": "es",51 "cleanup_voice": true52 }53 }'54```5556**Custom speaker voice cloning:**57```bash58curl -X POST https://api.eachlabs.ai/v1/prediction \59 -H "Content-Type: application/json" \60 -H "X-API-Key: $EACHLABS_API_KEY" \61 -d '{62 "model": "xtts-v2",63 "version": "0.0.1",64 "input": {65 "text": "This is a demonstration of voice cloning technology with natural-sounding speech output.",66 "speaker": "https://example.com/voice-sample.wav",67 "language": "en",68 "cleanup_voice": true69 }70 }'71```7273## Related Models7475- [openvoice](../openvoice/) - Voice cloning with style control76- [realistic-voice-cloning](../realistic-voice-cloning/) - RVC-based voice changer77- [incredibly-fast-whisper](../incredibly-fast-whisper/) - Audio transcription7879## Documentation8081- [each::labs Docs](https://docs.eachlabs.ai)82- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia