GET
/
api
/
v1
/
voices
curl -X GET https://app.dubformer.ai/api/v1/voices \
  -H "Authorization: Bearer YOUR_API_KEY"

{
  "voices": {
    "af-ZA": [
      {
        "name": "Adri",
        "voice_key": "53f154:af-ZA-AdriNeural",
        "style": "feminine"
      },
      {
        "name": "Willem", 
        "voice_key": "53f154:af-ZA-WillemNeural",
        "style": "masculine"
      }
    ],
    "en-US": [
      {
        "name": "Jenny",
        "voice_key": "53f154:en-US-JennyNeural",
        "style": "feminine"
      },
      {
        "name": "Guy",
        "voice_key": "53f154:en-US-GuyNeural", 
        "style": "masculine"
      },
      {
        "name": "Aria",
        "voice_key": "53f154:en-US-AriaNeural",
        "style": "feminine"
      }
    ],
    "es-ES": [
      {
        "name": "Elvira",
        "voice_key": "53f154:es-ES-ElviraNeural",
        "style": "feminine"
      },
      {
        "name": "Alvaro",
        "voice_key": "53f154:es-ES-AlvaroNeural",
        "style": "masculine"
      }
    ]
  }
}

curl -X GET https://app.dubformer.ai/api/v1/voices \
  -H "Authorization: Bearer YOUR_API_KEY"

​
Response

​
voices
object
Object with language codes as keys and arrays of voice objects as values.
{
  "voices": {
    "af-ZA": [
      {
        "name": "Adri",
        "voice_key": "53f154:af-ZA-AdriNeural",
        "style": "feminine"
      },
      {
        "name": "Willem", 
        "voice_key": "53f154:af-ZA-WillemNeural",
        "style": "masculine"
      }
    ],
    "en-US": [
      {
        "name": "Jenny",
        "voice_key": "53f154:en-US-JennyNeural",
        "style": "feminine"
      },
      {
        "name": "Guy",
        "voice_key": "53f154:en-US-GuyNeural", 
        "style": "masculine"
      },
      {
        "name": "Aria",
        "voice_key": "53f154:en-US-AriaNeural",
        "style": "feminine"
      }
    ],
    "es-ES": [
      {
        "name": "Elvira",
        "voice_key": "53f154:es-ES-ElviraNeural",
        "style": "feminine"
      },
      {
        "name": "Alvaro",
        "voice_key": "53f154:es-ES-AlvaroNeural",
        "style": "masculine"
      }
    ]
  }
}

​
Usage

When creating projects, the system automatically selects appropriate voices based on speaker detection and the target language. You don’t need to specify voices explicitly. Use these voice keys when creating re-translations to specify exact voices for each speaker.

​
Special Voice Keys

In addition to the specific voices listed, you can use these special voice keys:
  • soundalike - Uses AI-generated voices that match the original speaker characteristics
  • emotional_transfer - Uses emotional soundalike voices (less stable but more expressive)

​
Voice Availability

  • Not all languages have the same number of available voices
  • Voice availability may vary based on your subscription level
  • New voices are added regularly as our TTS providers expand their offerings
The voice list is continuously updated. Call this endpoint regularly to get the latest available voices for each language.