Everything on the Voice tab that governs how the agent sounds: the voice itself, the first thing it says, tone direction, pronunciation, and the room it appears to be sitting in. Turn-taking and the silence timers are on the same tab but are a subject of their own — see Turn-Taking, Interruptions and Dead Air.
agents:voice:manage permission.52 voices ship today, in two families:
| Family | Count | Labelled | Notes |
|---|---|---|---|
| Cartesia | 42 | Cartesia · <locale> · <gender> and Emotive where it applies |
English (incl. EN-US, EN-GB), Spanish, French, Hindi and Punjabi voices, plus ten tuned for emotional range |
| OpenAI Realtime | 10 | OpenAI Realtime · <style> |
Alloy, Ash, Ballad, Coral, Echo, Fable, Onyx, Nova, Sage, Shimmer — the only voices that accept written style direction |
If the agent already holds a voice id that is not in the grid, the picker says so underneath: "Custom voice ID in use: …". It still works; it simply is not one of the listed options.
The choice decides which speech engine runs the call. Picking one of the ten OpenAI names routes speech synthesis to OpenAI; anything else routes to Cartesia. That is why the next setting only applies to some voices.
Conversation Behavior → Voice-Specific Instructions is free text — "warm, unhurried, slightly lower pitch", "brisk and factual, no small talk".
It only has an effect on the ten OpenAI voices. They accept style direction as text; Cartesia voices do not read it. If you have picked a Cartesia voice and want a different feel, change the voice.
Tone that belongs in the instructions instead: how long turns should be, whether to use the caller's first name, how formal to be. Those are behavioural, and they work on every voice.
Conversation Behavior → Who Speaks First? has two values:
The greeting itself is on Setup → Instructions & Greeting → Static
Greeting. It is spoken verbatim, so it is the one line of the call you
control exactly. {{first_name}}, {{last_name}} and {{caller_number}}
resolve in it; an unknown caller resolves them to empty strings, so
Hi {{first_name}}, thanks for calling becomes Hi , thanks for calling —
write it as Hi, thanks for calling and let the instructions handle names.
Outbound calls behave differently on purpose: the agent waits for the callee to say something (up to 30 seconds) before it plays its opener, and plays it without allowing an interruption. Picking up a call and being talked over is the thing that makes an outbound robot obvious.
Voice delivery tags in the greeting are deliberate. The static greeting is the one place emotion markup may be authored inline, and it appears as written in the stored transcript. That is expected. Anywhere else in a call, the platform rules forbid the agent emitting those tags and they are stripped — the browser test panel flags such a turn with a small tags marker so you can report it.
Conversation Behavior → Voicemail Handling Instructions tells the agent what to do when an outbound call reaches an answering machine — leave a message (and which one), or hang up quietly.
It is required when the voicemail_detection tool is enabled, and the
field says so. Voicemail detection is an outbound-only behaviour; see
Placing Outbound Calls.
Pronunciation Packs (below the voice picker) rewrite words on their way to the speech engine, so your product and place names come out right instead of phonetically plausible. Packs come in four groups:
| Group | Behaviour |
|---|---|
| Always-On (Platform Core) | Applied to every agent; not switchable |
| Regional Packs | Opt in per agent — US, UK, Canadian English and French, French, Spanish and Mexican Spanish |
| Vertical Packs | Opt in per agent — automotive, finance, healthcare, home services, hospitality, legal, real estate |
| Tenant Custom | Your workspace's own entries; always applied |
Tick the packs this agent should carry. Each row shows the pack name, what it covers and an entry count.
A word still coming out wrong after the right pack is on usually needs a workspace entry rather than a pack — that is what Tenant Custom is for.
Background Audio (default on) plays quiet office ambience and keyboard typing while the agent is thinking. It exists because dead silence during a pause reads as a dropped call, and a caller who thinks the line dropped hangs up.
It only plays on telephony calls. Browser calls never get it, whatever this switch says.
Turn it off for agents where the illusion is wrong — an explicitly automated line, or a clinical or legal context where ambience is out of place.
{{first_name}} placeholder resolved empty
for an unknown caller. Remove it from the greeting.