Loading
Agentforce and Einstein Generative AI
Table des matières
Sélectionner des filtres

          Aucun résultat
          Aucun résultat
          Voici quelques conseils de recherche

          Vérifiez l'orthographe de vos mots-clés.
          Utilisez des termes de recherche plus généraux.
          Sélectionnez moins de filtres pour élargir votre recherche.

          Recherchez dans toute l’aide de Salesforce
          Set the Transcription Model for the Speech to Text Agent Action

          Set the Transcription Model for the Speech to Text Agent Action

          To control which model transcribes your audio, set the transcription model for the Speech to Text agent action.

          Required Editions

          Available in: Lightning Experience
          Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.
          User Permissions Needed  
          To build and manage Employee agents:

          Manage AI Agents

          OR

          Customize Application

          Note
          Note The Transcription Model parameter isn't available in the legacy Agentforce Builder. To set a transcription model, use Agentforce Builder in Agentforce Studio, Flow, or the REST API.
          1. From the App Launcher, search for Agent, and select the Agentforce Studio app, and then click Agents.
          2. Select the agent that you use to convert speech to text. If you don't have one, click New Agent and create one.
          3. On the Explorer panel, expand Subagents and select any subagent.
          4. Under Actions Available For Reasoning, expand Convert Speech to Text to show its input parameters.
          5. Next to Transcription Model, click Agent Populated. The Create Custom Variable dialog opens.
          6. Enter a Name for the variable. The API Name is populated automatically.
          7. For Data Type, select String.
          8. Optionally, enter a description to help the agent understand the variable's purpose.
          9. In the Default Value field, enter the transcription model value.
            Enter the exact value, such as whisper-v3-turbo or elevenlabs-scribe-v2. Any other value returns an invalid input error.
            Create Custom Variable dialog with the Default Value field set to a transcription model
          10. Save your changes.
           
          Chargement
          Salesforce Help | Article