Skip to main content
Every voice clone gets a unique voice ID: {Provider}.{Model}.{voice_id}
  • Telnyx: Telnyx.Qwen3TTS.33226e69-3abd-429b-b64a-86775c9b5850
  • Telnyx Ultra: Telnyx.Ultra.<provider_voice_id> (the provider_voice_id from the clone response)
  • Telnyx Bayan: Telnyx.Bayan.33226e69-3abd-429b-b64a-86775c9b5850
  • Minimax: Minimax.speech-2.8-turbo.TB4ZMVKanThGeldiw8rLBEg21v4ifjUTRgLpkodJxpMYV
  • Resemble: Resemble.<Model>.<clone_id>, where <Model> is the clone’s model_id (Pro, Turbo, or Urdu), for example Resemble.Turbo.33226e69-3abd-429b-b64a-86775c9b5850.
Find it in the Voice Design by clicking on any saved voice, or build it from the clone response’s provider, provider_supported_models, and provider_voice_id fields. Cloned voice usage, for every clone model, requires L2 identity verification or the voice.cloned_voice_usage: allowed capability on the organization. The first synthesis with a Bayan clone, right after it is created or after a service restart, takes about 1 second longer.

​
AI Assistants

Select your custom voice in the assistant’s voice settings. Qwen3TTS clones appear under Telnyx / Qwen3TTS, Minimax clones under Minimax. To use a Bayan clone, set the assistant voice to Telnyx.Bayan.<clone_id>. To use a Resemble clone, set it to Resemble.<Model>.<clone_id>.

​
Call Control

Pass the voice ID in the voice field of the speak command.

​
TTS WebSocket

Pass the voice ID as the voice query parameter on the WebSocket URL. Ultra clones are not available over WebSocket — use the REST API. See the TTS streaming guide for the full connection flow.