Skip to main content
PATCH
Update Call Agent

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Update call agent voice and personality settings.

end_call_on_recording_refusal
boolean | null

Whether to hang up the call if the user does not consent to recording

recording_disclaimer_required
boolean | null

Whether the call agent must include the recording disclaimer. Only Stuut staff can update this field.

outbound_begin_message
string | null

The opening line of the call agent.

voice_id
string | null

Voice DB ID (vce_...)

voice_speed
enum<string> | null

Voice speed

Available options:
slowest,
slow,
normal,
fast,
fastest
voice_temperature
number | null

Voice temperature 0.0-2.0

Required range: 0 <= x <= 2
language_code
string | null

BCP-47 starting language for the call agent (e.g. 'en-US', 'nl-NL'). When stt_mode=AUTO, this is the starting hint (observer may swap). When stt_mode=OFF, this is a hard pin and required. Overridden per-call by partner.retell_language_code when set.

stt_mode
enum<string> | null

STT model selection mode for voice agents.

AUTO: Multilingual Scribe (never pinned) + LanguageObserver hot-swaps STT to the detected language; a configured language_code is only a detection hint. FLUX: Legacy — equivalent to OFF + English (Deepgram Flux, built-in turn detection). Hidden from the dropdown; kept for existing rows. No observer; ignores language_code. OFF: Hard pin to language_code (required) — Flux when English, else pinned Scribe. No observer. SCRIBE: Legacy multilingual Scribe, no observer. Hidden from the UI; kept for existing rows.

Available options:
auto,
flux,
off,
scribe
custom_prompt
string | null

Admin-only override for the base outbound prompt. Jinja-rendered against the call context. Include {{ base_prompt }} anywhere in the text to inject the rendered OUTBOUND_AGENT_TEMPLATE at that position; omit the token to fully replace the base prompt.

Response

Successful Response

Call agent with current voice details.

id
string
required
end_call_on_recording_refusal
boolean
required
recording_disclaimer_required
boolean
required
outbound_begin_message
string | null
required
voice_id
string | null
required
voice
Voice · object | null
required

ElevenLabs voice from the synced voice catalog.

voice_speed
enum<string>
required
Available options:
slowest,
slow,
normal,
fast,
fastest
voice_temperature
number
required
stt_mode
enum<string>
required

STT model selection mode for voice agents.

AUTO: Multilingual Scribe (never pinned) + LanguageObserver hot-swaps STT to the detected language; a configured language_code is only a detection hint. FLUX: Legacy — equivalent to OFF + English (Deepgram Flux, built-in turn detection). Hidden from the dropdown; kept for existing rows. No observer; ignores language_code. OFF: Hard pin to language_code (required) — Flux when English, else pinned Scribe. No observer. SCRIBE: Legacy multilingual Scribe, no observer. Hidden from the UI; kept for existing rows.

Available options:
auto,
flux,
off,
scribe
language_code
string | null
required
custom_prompt
string | null
required