One voice for the whole call

Steps

1. Each call speaks in one voice from the first sentence to the last: the line's voice, else the workspace voice chosen on AI voices.
2. In a test call in the browser, the voice is decided on the first sentence and kept for every later sentence and turn.
3. If that voice cannot make one sentence, the sentence is shown in the transcript and is not spoken in another voice.
4. Every sentence uses the same audio format, so pieces join without a change in sound.

Tips

• To change the voice, change it on AI voices; the next call uses the new one.

Good to know

• A sentence the voice could not make after its retries is left out of the audio, not read by your browser.

Related how-tos

• AI voices Choose the voice your AI receptionist speaks with on calls, tune how it sounds, teach it how to read names, and clone your own voice.
• Set the language calls start in Choose the language your AI agent greets callers in on a line.