Get Voices

GET

https://api.smallest.ai/waves/v1/:model/get_voices

GET

/waves/v1/:model/get_voices

from smallestai import SmallestAI
client = SmallestAI(
    token="YOUR_TOKEN_HERE",
)
client.waves.get_voices(
    model="lightning-v3.1",
)

{
  "voices": [
    {
      "voiceId": "avery",
      "displayName": "Avery",
      "tags": {
        "language": [
          "english"
        ],
        "accent": "american",
        "gender": "female",
        "age": "young",
        "emotions": [],
        "usecases": [
          "conversational"
        ]
      }
    },
    {
      "voiceId": "liam",
      "displayName": "Liam",
      "tags": {
        "language": [
          "english"
        ],
        "accent": "british",
        "gender": "male",
        "age": "young",
        "emotions": [],
        "usecases": [
          "conversational"
        ]
      }
    },
    {
      "voiceId": "devansh",
      "displayName": "Devansh",
      "tags": {
        "language": [
          "hindi",
          "english"
        ],
        "accent": "indian",
        "gender": "male",
        "age": "young",
        "emotions": [],
        "usecases": [
          "conversational"
        ]
      }
    },
    {
      "voiceId": "mishka",
      "displayName": "Mishka",
      "tags": {
        "language": [
          "hindi",
          "english",
          "marathi",
          "gujarati",
          "punjabi",
          "bengali",
          "odia",
          "tamil",
          "telugu"
        ],
        "accent": "indian",
        "gender": "female",
        "age": "young",
        "emotions": [],
        "usecases": [
          "conversational"
        ]
      }
    }
  ]
}

Return the voice catalog for the chosen Lightning v3.1 pool. Two pools:

lightning-v3.1 — the Standard catalog. Supports voice cloning; 20 language codes.
lightning-v3.1-pro — the Pro catalog. Curated set across American, British, and Indian accents plus 29 additional languages. Same latency and concurrency as Standard, on dedicated inference.

The endpoint is pool-scoped: /waves/v1/lightning-v3.1/get_voices returns Standard voices only; /waves/v1/lightning-v3.1-pro/get_voices returns Pro voices only. Call one or both depending on which pool you plan to use.

Each voice carries tags (language, accent, gender, age, emotions, usecases). Filter client-side to find the voices that match a target language, accent, or use case. Pass the returned voiceId as voice_id on the unified POST /waves/v1/tts route, together with "model": "lightning_v3.1" (Standard) or "model": "lightning_v3.1_pro" (Pro).

For the canonical per-language voice list (with previews and recommended pairings), see the Lightning v3.1 and Lightning v3.1 Pro model cards.

Path parameters

modelenumRequiredDefaults to lightning-v3.1

The pool to query. lightning-v3.1 returns Standard voices; lightning-v3.1-pro returns Pro voices. Note the hyphenated path form differs from the underscored body form used on POST /waves/v1/tts (lightning_v3.1, lightning_v3.1_pro).

Allowed values:

Response

Voices retrieved successfully.

voiceslist of objectsOptional

List of available voices for the chosen pool.

Errors

400

Bad Request Error

401

Unauthorized Error

500

Internal Server Error