Skip to main content
POST
voice.assistant.create

Authorizations

Authorization
string
header
required

API key: sk_live_…

Headers

Idempotency-Key
string
required

Required: this capability has an external effect.

Maximum string length: 255
Pramaan-Max-Price-Micro
string

Optional. The most this request may be priced at, in micro-USD (a whole number above 0). It replaces the capability's own price ceiling for this request, lower or higher. Sources that could cost more are left out; when none is left the answer is 400 with the lowest limit that would work.

Pattern: ^[1-9]\d{0,14}$

Body

application/json
name
string
required

Your unique name for this configuration, up to 40 letters, digits, underscores or hyphens.

Required string length: 1 - 40
Pattern: ^[a-zA-Z][a-zA-Z0-9_-]*$
prompt
string
required

Instructions for the speaking agent; may contain personal data.

Required string length: 1 - 10000
voice
enum<string>

The speaking voice, one of the listed keys. Leave out for the standard voice. Voices sound different on different kinds of assistant; test with a call.

Available options:
default,
female-1,
female-2,
female-3,
male-1,
male-2,
male-3
voiceRef
string

The ref returned by audio.voices.list; selection is not available yet.

Pattern: ^(ref_[0-9A-HJKMNP-TV-Z]{26}|rh_[A-Za-z0-9_-]{24,1024})$
knowledgeBaseRef
string

The ref returned by voice.knowledge-bases.list; use a ready, paid base belonging to you.

Pattern: ^(ref_[0-9A-HJKMNP-TV-Z]{26}|rh_[A-Za-z0-9_-]{24,1024})$
messages
object[]

Up to 20 additional conversation messages.

Maximum array length: 20
greeting
string

First spoken message; empty clears it.

Maximum string length: 1000
language
enum<string>
default:en

Speech recognition language.

Available options:
en,
es,
fr,
de,
it,
pt,
hi,
ja,
zh
tier
enum<string>
default:standard

Service tier. Premium must be selected explicitly.

Available options:
standard,
premium
maxDurationSeconds
integer
default:120

Maximum call length, 10 to 600 seconds.

Required range: 10 <= x <= 600
recording
boolean
default:false

Whether to record speech; default false.

tools
string[]

Names of tools created by you.

Maximum array length: 20

Your unique name for this configuration, up to 40 letters, digits, underscores or hyphens.

Required string length: 1 - 40
Pattern: ^[a-zA-Z][a-zA-Z0-9_-]*$
backgroundSound
enum<string>
default:off

Built-in background sound.

Available options:
off,
office
waitSeconds
number
default:0.4

Pause before speaking, 0 to 5 seconds.

Required range: 0 <= x <= 5
interruptionWords
integer
default:2

Words needed to interrupt the agent, 0 to 10.

Required range: 0 <= x <= 10
voicemailMessage
string

Message to leave on voicemail; empty clears it.

Maximum string length: 1000
endCallMessage
string

Message before hanging up; empty clears it.

Maximum string length: 1000
endCallPhrases
string[]

Up to 20 phrases that end a call.

Maximum array length: 20
Required string length: 1 - 100

Response

The result

name
string
required

Your unique name for this configuration, up to 40 letters, digits, underscores or hyphens.

Required string length: 1 - 40
Pattern: ^[a-zA-Z][a-zA-Z0-9_-]*$
prompt
string
required

Instructions for the speaking agent; may contain personal data.

Required string length: 1 - 10000
language
enum<string>
default:en
required

Speech recognition language.

Available options:
en,
es,
fr,
de,
it,
pt,
hi,
ja,
zh
tier
enum<string>
default:standard
required

Service tier. Premium must be selected explicitly.

Available options:
standard,
premium
maxDurationSeconds
integer
default:120
required

Maximum call length, 10 to 600 seconds.

Required range: 10 <= x <= 600
recording
boolean
default:false
required

Whether to record speech; default false.

tools
string[]
required

Names of tools created by you.

Maximum array length: 20

Your unique name for this configuration, up to 40 letters, digits, underscores or hyphens.

Required string length: 1 - 40
Pattern: ^[a-zA-Z][a-zA-Z0-9_-]*$
backgroundSound
enum<string>
default:off
required

Built-in background sound.

Available options:
off,
office
waitSeconds
number
default:0.4
required

Pause before speaking, 0 to 5 seconds.

Required range: 0 <= x <= 5
interruptionWords
integer
default:2
required

Words needed to interrupt the agent, 0 to 10.

Required range: 0 <= x <= 10
endCallPhrases
string[]
required

Up to 20 phrases that end a call.

Maximum array length: 20
Required string length: 1 - 100
voice
enum<string>

The speaking voice, one of the listed keys. Leave out for the standard voice. Voices sound different on different kinds of assistant; test with a call.

Available options:
default,
female-1,
female-2,
female-3,
male-1,
male-2,
male-3
voiceRef
string

The ref returned by audio.voices.list; selection is not available yet.

Pattern: ^(ref_[0-9A-HJKMNP-TV-Z]{26}|rh_[A-Za-z0-9_-]{24,1024})$
knowledgeBaseRef
string

The ref returned by voice.knowledge-bases.list; use a ready, paid base belonging to you.

Pattern: ^(ref_[0-9A-HJKMNP-TV-Z]{26}|rh_[A-Za-z0-9_-]{24,1024})$
messages
object[]

Up to 20 additional conversation messages.

Maximum array length: 20
greeting
string

First spoken message; empty clears it.

Maximum string length: 1000
voicemailMessage
string

Message to leave on voicemail; empty clears it.

Maximum string length: 1000
endCallMessage
string

Message before hanging up; empty clears it.

Maximum string length: 1000