Voice Library

Verbatik provides access to over 2,700 pre-trained voices across dozens of languages and dialects.

Voice Properties

Each voice has:

• A unique slug (e.g., jenny-en-us) used as the voice ID in API calls.
• A display name (e.g., "Jenny").
• A language code (e.g., en-US) and language name.
• A gender classification: Male, Female, or Neutral.
• A neural flag indicating higher-quality neural synthesis.
• Optional voice styles for voices that support multiple speaking styles.

Browsing Voices via the API

GET /api/v1/voices

Query Parameters:

Example:

curl -X GET "https://api.verbatik.com/api/v1/voices?language=en-US&gender=Female" \
  -H "Authorization: Bearer vbt_your_api_key"

Response:

[
  {
    "id": "jenny-en-us",
    "name": "Jenny",
    "gender": "Female",
    "language_code": "en-US",
    "language_name": "English (United States)",
    "is_neural": true,
    "sample_url": "https://...",
    "styles": ["cheerful", "sad", "angry", "excited"]
  }
]

Supported Languages

Favorite Voices

You can mark voices as favorites in the dashboard for quick access. Favorites are saved per user and persist across sessions.

Using a Voice

Pass the voice slug as the X-Voice-ID header in your TTS requests:

curl -X POST https://api.verbatik.com/api/v1/tts \
  -H "Authorization: Bearer vbt_your_api_key" \
  -H "Content-Type: text/plain" \
  -H "X-Voice-ID: jenny-en-us" \
  --data "Hello from Jenny!" \
  --output jenny.mp3

If you don't specify a voice, the default voice (Jenny, English US) is used.

Voice Styles

Some voices (particularly neural voices) support multiple speaking styles listed in the styles field. Styles can include:

• Cheerful, Sad, Angry, Excited
• Friendly, Whispering
• And more, depending on the voice.

Style support varies by voice and provider.