- Python
- TypeScript
call.set_persona() is deliberately minimal. Give it the organization name and let the agent figure out the tone. You don’t need to specify a voice style, a greeting template, or a list of prohibited phrases — Guava’s defaults are professional and natural.signature
call.set_persona(
organization_name: str | None = None,
agent_name: str | None = None,
agent_purpose: str | None = None,
voice: str | None = None,
speech_speed: Literal["x-slow", "slow", "medium", "fast", "x-fast"] | None = None,
)
| Parameter | Type | Default | Description |
|---|---|---|---|
organization_name | str | None | — | The organization the agent represents. Used in introductions. |
agent_name | str | None | — | The agent’s first name. Defaults to a generic ‘assistant’ style. |
agent_purpose | str | None | — | A sentence describing why the agent is calling. Sets the LLM’s operating context. |
voice | str | None | "grace" | The TTS voice to use. Options: "grace" (Southeastern U.S. female), "andie" (U.S. female), "otto" (U.S. male), "colin" (U.S. male), "kyle" (U.S. male), "kate" (British female), or "jack" (British male). For languages outside of English, only the "grace" voice is supported. |
speech_speed | str | None | "medium" | How quickly the agent speaks. Options: "x-slow", "slow", "medium", "fast", or "x-fast". Changing it mid-call takes effect on the agent’s next utterance. |
call.setPersona() is deliberately minimal. Give it the organization name and let the agent figure out the tone. You don’t need to specify a voice style, a greeting template, or a list of prohibited phrases — Guava’s defaults are professional and natural.signature
await call.setPersona({
organizationName?: string,
agentName?: string,
agentPurpose?: string,
voice?: string,
speechSpeed?: "x-slow" | "slow" | "medium" | "fast" | "x-fast",
})
| Parameter | Type | Default | Description |
|---|---|---|---|
organizationName | string | — | The organization the agent represents. Used in introductions. |
agentName | string | — | The agent’s first name. Defaults to a generic ‘assistant’ style. |
agentPurpose | string | — | A sentence describing why the agent is calling. Sets the LLM’s operating context. |
voice | string | "grace" | The TTS voice to use. Options: "grace" (Southeastern U.S. female), "andie" (U.S. female), "otto" (U.S. male), "colin" (U.S. male), "kyle" (U.S. male), "kate" (British female), or "jack" (British male). For languages outside of English, only the "grace" voice is supported. |
speechSpeed | string | "medium" | How quickly the agent speaks. Options: "x-slow", "slow", "medium", "fast", or "x-fast". Changing it mid-call takes effect on the agent’s next utterance. |
Example
- Python
- TypeScript
example.py
call.set_persona(
organization_name="Bright Smile Dental",
agent_name="Alex",
agent_purpose="You are calling patients to help them schedule and confirm dental appointments",
voice="grace",
)
Include the contact’s name in
agent_purpose to help the agent personalize the conversation naturally.example.ts
await call.setPersona({
organizationName: "Bright Smile Dental",
agentName: "Alex",
agentPurpose: "Help patients schedule dental appointments",
})
Include the contact’s name in
agentPurpose to help the agent personalize the conversation naturally.