GET
/
v1
/
voices
Get Voices
curl --request GET \
  --url https://api.typecast.ai/v1/voices \
  --header 'X-API-KEY: <api-key>'
[
  {
    "voice_id": "tc_62a8975e695ad26f7fb514d1",
    "voice_name": "Olivia",
    "model": "ssfm-v21",
    "emotions": [
      "tonemid",
      "toneup",
      "normal",
      "happy",
      "sad",
      "angry"
    ]
  }
]

Authorizations

​
X-API-KEY
string
header
required

API key for authentication. You can obtain an API key from the Typecast dashboard.

Query Parameters

​
model
enum<string>

Voice model to use

Available options:
ssfm-v21

Response

200
application/json

Success - Returns list of available voice models

​
voice_id
string
required

Unique identifier for the voice using a standardized format.

Format begins with 'tc_' for official Typecast voices or 'uc_' for user-created custom voices, followed by a unique alphanumeric string.

This ID is required for all voice-related API operations.

Example:

"tc_62a8975e695ad26f7fb514d1"

​
voice_name
string
required

Human-readable name of the voice. This provides a friendly identifier that can be displayed to users in voice selection interfaces.

Names are typically representative of the voice characteristics or intended persona.

Example:

"Olivia"

​
model
enum<string>
required

The underlying TTS model technology used by this voice. Currently supports 'ssfm-v21' (Speech Synthesis Foundation Model v2.1), which provides high-quality neural text-to-speech synthesis with advanced prosody and emotion support.

Available options:
ssfm-v21
​
emotions
string[]
required

Array of emotion labels supported by this voice. Each voice supports a specific set of emotions that can be applied during speech synthesis to convey different tones.

Common emotions include 'happy', 'sad', 'normal', and 'angry', with varying levels of intensity possible for each emotion type.

Example:
[
  "tonemid",
  "toneup",
  "normal",
  "happy",
  "sad",
  "angry"
]