Get more control over how your audio is transcribed. The Transcription Model parameter provides two models, Whisper V3 Turbo and ElevenLabs Scribe V2, for the Convert speech to text and Convert Base64 speech to text actions to fit your transcription needs, such as audio quality, language, and data handling requirements. This parameter is available in Agentforce Builder, Flow, and REST.
Where: This change applies to the Convert speech to text and Convert Base64 speech to text actions in Flow Builder, Agentforce Builder, and the REST API.
How: In Flow Builder, add a Convert speech to text or Convert Base64 speech to text action to your flow. In the Transcription Model field, select Whisper V3 Turbo or ElevenLabs Scribe V2. If you don't select a model, Whisper V3 Turbo is used by default.