Developer & API Integrations
WORKINGVoice IDs
Voice ID reference, synthesis models, language accents, and audio configuration parameters for ESER AI video rendering.
## Voice IDs & Audio Synthesis Reference
The ESER AI Voice Engine provides studio-grade AI narration for vertical video reels, shorts, and slideshow audio tracks.
### Supported Voice Models & Accents
- **Alloy / Onyx / Echo / Shimmer (OpenAI TTS):** Standard crisp voiceovers (1 AI credit per 100 characters).
- **Adam / Rachel / Antoni / Bella (ElevenLabs Studio):** Hyper-realistic emotive voices with natural pacing (2 AI credits per 100 characters).
- **Supported Languages:** English (US, UK, AU, IN), Spanish, French, German, Portuguese, Italian, Japanese, Hindi.
---
### REST API Integration
To query available voice identifiers programmatically:
```bash
curl -X GET https://app.eserai.tech/v1/accounts/voice-ids \
-H "Authorization: Bearer YOUR_ESER_API_KEY"
```
#### Response Schema
```json
{
"voices": [
{ "id": "alloy", "name": "Alloy", "gender": "neutral", "provider": "openai", "tier": "all" },
{ "id": "eleven_rachel", "name": "Rachel", "gender": "female", "provider": "elevenlabs", "tier": "pro_agency" }
]
}
```
Was this article helpful?
Reach ESER TECH support for assistance with account setup or API integration.