Get all available Text-to-Speech (TTS) voices from supported providers

Retrieves a comprehensive list of available TTS voices from all supported providers including ElevenLabs, Cartesia, and Dasha. Each voice includes metadata such as language, gender, description, and audio preview URLs for voice selection in agent configuration.

Supported Voice Providers:

• ElevenLabs: Premium AI voices with natural speech patterns and emotions
• Cartesia: Fast, high-quality voices optimized for real-time conversation
• Dasha: Platform-native voices with consistent quality and low latency

Voice Categories:

• Public: Pre-trained voices available to all users
• Cloned: Custom voices created from voice samples (organization-specific)

Voice Selection Considerations:

• Language compatibility with your target audience
• Voice characteristics (gender, age, accent, tone)
• Provider-specific features (emotion, stability, clarity)
• Performance requirements (latency vs quality)
• Cost implications (premium vs standard voices)

Common Use Cases:

• Agent configuration voice selection interface
• Voice preview and testing in admin dashboards
• Dynamic voice switching based on call context
• Multi-language agent setup with appropriate voices

GET /api/v1/voice

Get all available Text-to-Speech (TTS) voices from supported providers

JavaScript

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://blackbox.dasha.ai/api/v1/voice', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

200

[
  {
    "id": "<string>",
    "provider": "ElevenLabs",
    "category": "Public",
    "name": "<string>",
    "voiceId": "<string>",
    "description": "<string>",
    "language": "<string>",
    "labels": {},
    "previewUrl": "<string>",
    "createdTime": "2023-11-07T05:31:56Z",
    "lastUpdatedTime": "2023-11-07T05:31:56Z"
  }
]

Response

200

application/json

Returns the list of available voices

id · string · required

Unique identifier for the voice

Minimum string length: 1

provider · enum<string> · required

TTS provider (ElevenLabs, Cartesia, Dasha, Inworld, Lmnt)

Available options: ElevenLabs, Cartesia, Dasha, Inworld, Lmnt

category · enum<string> · required

Voice category (Public or Cloned)

Available options: Public, Cloned

name · string | null

Display name of the voice

voiceId · string | null

Voice ID used for synthesis

description · string | null

Description of voice characteristics

language · string | null

Primary language for the voice

labels · object

Custom metadata labels

Show child attributes

previewUrl · string | null

URL for voice preview audio

createdTime · string<date-time> | null

Timestamp when voice was created

lastUpdatedTime · string<date-time> | null

Timestamp when voice was last updated