Use the Speech To Text action to convert audio files into text during agent interactions and automated workflows. Agents can accept an audio file ID and return a transcript for use in conversations or downstream automation. The action supports multiple languages and common audio formats such as MP3, WAV, FLAC, OGG, OGA, AMR, MPEG, MPGA. The Speech To Text action is available in the Agentforce Builder, Flow, REST, and Apex.
Where: This change applies to Lightning Experience in Enterprise, Performance, Unlimited, and Developer Editions with Foundations or Agentforce 1 Editions.
When: This change is available starting from February 17, 2026.
How: In Agentforce Builder, in the Conversation Preview, enter convert speech to text, provide the Audio File ID when prompted, and click Submit.