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.

{
  "voices": [
    {
      "voiceId": "avery",
      "displayName": "Avery",
      "tags": {
        "language": [
          "english"
        ],
        "accent": "american",
        "gender": "female",
        "age": "young",
        "emotions": [],
        "usecases": [
          "conversational"
        ]
      }
    }
  ]
}