Voice
The voice the caller hears, its speed and tone, the greeting, and pronunciation of tricky words.
Pick a voice
The Voice drawer sets the text-to-speech voice, speed and tone. Transcription settings are in Transcription. Browse the list and press play on any voice before you commit. A voice that reads well on paper can land wrong on a phone speaker.
A brand-new agent starts on a default voice, Ella, with a fallback voice from a different provider already set.
The default voice is a reasonable neutral starting point, but pick the voice that fits the business rather than leaving it in place.
Speed
Playback rate from 0.6x to 1.5x in 0.1x steps. Around natural pace is usually best: too fast reads as rushed, too slow as robotic. Use the play button on the Speed and tone card to hear the current speed and tone before you save.
Tone
An emotional colour for the voice. The available control depends on the engine behind the voice you picked: some voices take an emotion preset, others an expressiveness preset.
Emotion presets
On voices that take it, the emotion control offers six presets.
| Value | Reads as |
|---|---|
| Neutral | Even, no colour |
| Content | Settled, at ease |
| Happy | Bright, upbeat |
| Surprised | Raised, reactive |
| Sad | Subdued |
| Angry | Sharp (rarely useful for a customer line) |
Expressiveness presets
The other voices take an expressiveness preset instead: Natural, Expressive, or Steady. A support line usually wants the even end of the range.
The greeting
The greeting is the first thing a caller hears. You write it under Greeting in the Build document, above the Instructions.
It is spoken word for word the instant the call connects, straight to the voice engine, skipping the model round-trip. That is what makes the open of a call instant and consistent.
A new voice agent starts with a plain greeting:
Hello, how can I help?
When onboarding knows the business name, the greeting names it:
Hello, you've reached Mitchell's Plumbing. How can I help?
Turning it off
You can turn the Fixed greeting switch off. The runtime then falls back to a greeting the model generates on the spot, which costs you the instant first speech.
A good greeting is short and names the business. That one line sets the tone for the whole call.
Pronunciation
A pronunciation entry teaches the voice how to say a word it would otherwise mangle: a brand name, a place, an acronym, or jargon. Add the word and how it should sound.
Pronunciation fixes what the agent says. Recognition hints in Transcription fix what it hears. A brand name or product range usually wants both. Both are agent-wide rather than per version, so a change reaches live calls as soon as it saves.