CX Agent Studio seamlessly provides speech-to-text (STT),
text-to-speech (TTS), and custom voice capabilities.

## Voice

You can adjust the following
[agent application settings](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/settings.md.txt#application)
related to speech synthesis:

- **Voice**:
  The voice used for speech synthesis.
  You can select from built-in voices
  or custom voices that you previously created.

- **Custom Voices**:
  Create a custom voice by uploading an audio file.
  You must attest that you have the speaker's permission
  to clone the voice before uploading.
  You can edit or delete existing custom voices.
  Supported formats are WAV, MP3, M4A, OGG, and FLAC.
  The audio must be at least 15 seconds and up to 60 seconds.
  The maximum file size is 10 MB.

  > [!NOTE]
  > **Note:** You can also use [AI Assist](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/ai-assist) to generate or modify custom voices (for example, adding an accent) directly from uploaded files.

- **Speaking style**:
  You can control the tempo of the voice.

## Speech (STT) and DTMF

You can adjust the following
[agent application settings](https://docs.cloud.google.com/gemini-enterprise-cx/cx-agent-studio/settings.md.txt#application)
related to speech and DTMF processing:

- **Silence timeout**: Wait for user input, then prompt them to re-engage.
- **Ambient sound volume gain**: Adjust the ambient sound volume.
- **Keypad input**: Set up dual-tone multi-frequency (DTMF) for telephone calls. Enabled by default.