Skip to main content
Choose speech mode and language before selecting a voice. These settings determine which voices and speech-recognition fields apply.

​
Discover voices

Call GET /api/v2/agent/voices?targetAccountId=.... Store the returned voice id in agentVoice; do not store its display name. Each catalog entry describes supported languages, compatible speech-to-speech engines, standard text-to-speech support, account availability, and any missing plan requirement.

​
Language

agentLang accepts the language modes documented by the Agent update schema. Match the selected voice to that language. Use the multilingual mode only when the conversation must move between supported languages.

​
Standard speech mode

Set agentS2SEngine to null. Separate recognition and synthesis settings can then apply:
  • agentSttEngine
  • agentSttSmartFormatting
  • agentTtsEngine
  • agentVoice
Choose a voice whose catalog entry reports supportsStandardTts: true and includes the selected language.

​
Speech-to-speech mode

Set agentS2SEngine to a supported engine: openai or gemini. Choose a voice whose compatibleS2SEngines includes that engine. Separate STT and TTS settings may not apply in this mode. Vida manages the supported real-time model behind each engine as capabilities are released. Upcoming OpenAI support includes gpt-live-1. Read staging after the update and verify language, mode, and exact voice ID together. Test a staged call before publishing.