Concepts
Voice & language
Voice options, model runtime, and language support.
OpenPhn runs the conversation through Gemini Live at the call runtime today. Voice options and language codes are exposed via the API; additional TTS providers (ElevenLabs, Google Cloud TTS) ship in a future release.
List voices
curl https://api.openphn.com/v1/voices \
-H "Authorization: Bearer sk_live_..."Each entry includes provider, gender, language, and a preview URL.
Choose a voice on call create
Pass voice_id (and optionally voice_engine, language) on
POST /v1/calls:
{
"to": "+14155551234",
"objective": "...",
"outcome_schema": { ... },
"consent_type": "prior_express",
"voice_id": "puck",
"voice_engine": "gemini_25",
"language": "en-US"
}voice_engine—gemini_25(default) orgemini_31.language— BCP-47 (en-US,es-US,fr-FR, etc.) passed through to Gemini Live.
Static voice list today. ElevenLabs and Google Cloud TTS are wired for
previews but do not yet run at call time. When they ship you'll see
additional provider entries in /v1/voices without any API break.