> ## Documentation Index
> Fetch the complete documentation index at: https://docs.praxis-ai.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Voice turn prediction check (is the speaker done, is it the same request, is it an interruption)
> Asks the turn-prediction model one question about the words heard so far, so the
voice client can start answering before the speech-to-text end of turn. No credits
are used. The effective mode comes from the twin's voice turn prediction setting and
the server switches; when it is off the answer is `{ ok:false, error:'off' }`.
`barge` is answered only when barge-in prediction is enabled as well.
Phases: `listen` (is the speaker done; optionally which lookup the answer needs),
`drift` (would a reply to `earlier` still answer `heard`), `end` (done, and the same
question when `earlier` is set), `barge` (is the user taking the turn while the twin
speaks `lastAssistant`), `react` (how the speaking twin's face and voice should react to
words that did not interrupt it; answered only when the session's `turn_predict.react`
is set, else `react-off`), `warm` (opens the connection before the first check; no
`heard`; always answers `{ ok:true }` at once).
Every failure (off, timeout, busy, rate) is a `200` with `ok:false`; only a
malformed body is a `400`. The text is never logged or stored.
## OpenAPI
````yaml /mdx/api-reference/runtime/runtime-api.json post /api/ai/rtProxy/turnPredict
openapi: 3.0.0
info:
title: Pria Runtime API
version: 2.0.262
description: >-
Pria API Documentation Praxis's developer platform is a core part of our
mission to empower organizations to grow better. Our APIs are designed to
enable teams of any shape or size to build robust integrations that help
them customize and get the most value out of Pria. All Pria APIs are built
using REST conventions and designed to have a predictable URL structure.
They use many standard HTTP features, including methods (POST,
GET, PUT, DELETE) and error response codes.
All API calls are
made under https://hiimpria.ai/api and all responses return standard JSON.
In these docs, you'll find lists of all available endpoints for a given API,
along with interactive code blocks for building requests. For walkthroughs
of basic usage for these APIs, check out the API guides.
A
session that a course page (Canvas) opened for an administrator — or that a
Digital Twin's sign-in provider opened for one of its people — starts with
user rights in that twin only: until the person confirms it's them with a
code (POST /api/user/launch-scope/challenge, then /api/auth/mfa-resend and
/api/auth/mfa-verify), every route outside that twin's day-to-day work
answers 403 with code LAUNCH_SCOPE_STEP_UP and the twin's id.
servers:
- url: https://pria.praxislxp.com
description: Pria API Server
security: []
tags:
- name: Authentication
description: User authentication, registration, and password management (/api/auth)
- name: OAuth
description: OAuth authentication providers - Google, GitHub, SSO (/api/auth/oauth)
- name: User
description: User profile management and account operations (/api/user)
- name: User Institutions
description: User institution memberships and switching (/api/user/institution)
- name: User Tools
description: Available tools for authenticated users (/api/user/tools)
- name: Institutions
description: Institution settings and configuration (/api/user/institution)
- name: Conversation
description: AI conversation and Q&A endpoints (/api/ai)
- name: Realtime
description: Real-time voice AI and WebRTC sessions (/api/ai/rt)
- name: Assistant
description: AI assistant configuration and management (/api/user/assistant)
- name: History
description: Conversation history and favorites (/api/user/history)
- name: RAG
description: >-
Document upload, embedding, and retrieval-augmented generation
(/api/user/files, /api/user/rag)
- name: Setting
description: Instance variables and settings management (/api/user/setting)
- name: Branding
description: Digital twin branding and customization (/api/agent/branding)
- name: Agent
description: Agent engagement and session management (/api/agent)
- name: SDK Launch
description: >-
SDK launch token signing and verification for secure iframe embedding
(/api/auth/sdk-sign, /api/auth/sdk-verify)
- name: Testing
description: Health checks, diagnostics, and test endpoints (/api/test)
- name: Admin Accounts
description: Account management for super admins (/api/admin/account)
- name: Admin Institutions
description: Institution management for admins (/api/admin/institution)
- name: Admin Users
description: User management for admins (/api/admin/user)
- name: Admin Entitlements
description: >-
User-institution relationships and permissions
(/api/admin/userInstitution)
- name: Admin Sessions
description: Session management for admins (/api/admin/session)
- name: Admin Histories
description: Conversation history management and analytics (/api/admin/history)
- name: Admin Assistants
description: AI assistant management for admins (/api/admin/assistant)
- name: Admin Questions
description: Institution question and prompt management (/api/admin/question)
- name: Admin Tools
description: Tool configuration management (/api/admin/tool)
- name: Admin AI Models
description: AI model configuration (/api/admin/aimodel)
- name: Admin MCP Servers
description: Model Context Protocol server management (/api/admin/mcpserver)
- name: Admin Feedbacks
description: User feedback management (/api/admin/feedback)
- name: Admin Uploads
description: Upload management (/api/admin/upload)
- name: Admin Charts
description: Analytics and visualization chart management (/api/admin/chart)
- name: Audio Notes
description: Capture and ingest spoken notes into the personal vault
- name: Memory
description: User-facing memory parameters (personal + shared instance memory).
- name: My Data
description: >-
GDPR controls — personal-scope counts, async ZIP-by-email export, and
scoped soft-delete. Every endpoint pins `user = req.user._id` AND
`institution: null`; institution-scoped data is governed by the
institution's own retention policy and never reached from here.
- name: Questions
description: >-
User-facing read of the onboarding question bank used by the "create a
digital twin" wizard.
- name: Transcription
description: >-
One-shot speech-to-text for in-place dictation. Audio blob in, transcript
out — no Upload / History / RAG embeddings are persisted. Use
`/audio-notes` for anything durable.
paths:
/api/ai/rtProxy/turnPredict:
post:
tags:
- Realtime
summary: >-
Voice turn prediction check (is the speaker done, is it the same
request, is it an interruption)
description: >
Asks the turn-prediction model one question about the words heard so
far, so the
voice client can start answering before the speech-to-text end of turn.
No credits
are used. The effective mode comes from the twin's voice turn prediction
setting and
the server switches; when it is off the answer is `{ ok:false,
error:'off' }`.
`barge` is answered only when barge-in prediction is enabled as well.
Phases: `listen` (is the speaker done; optionally which lookup the
answer needs),
`drift` (would a reply to `earlier` still answer `heard`), `end` (done,
and the same
question when `earlier` is set), `barge` (is the user taking the turn
while the twin
speaks `lastAssistant`), `react` (how the speaking twin's face and voice
should react to
words that did not interrupt it; answered only when the session's
`turn_predict.react`
is set, else `react-off`), `warm` (opens the connection before the first
check; no
`heard`; always answers `{ ok:true }` at once).
Every failure (off, timeout, busy, rate) is a `200` with `ok:false`;
only a
malformed body is a `400`. The text is never logged or stored.
requestBody:
required: true
content:
application/json:
schema:
type: object
required:
- phase
properties:
phase:
type: string
enum:
- listen
- drift
- end
- barge
- react
- warm
heard:
type: string
description: >-
The words heard so far (capped at 2000 characters). Required
for every phase except `warm`.
earlier:
type: string
description: >-
The text an earlier held answer was started for (drift and
end).
lastAssistant:
type: string
description: >-
What the twin said last, or is saying now for barge and
react (capped at 600 characters).
specId:
type: string
pattern: ^[A-Za-z0-9_-]{1,64}$
requestArgs:
type: object
description: Only the two fields that pick the conversation.
properties:
conversationId:
type: string
selectedCourse:
type: object
properties:
course_id:
type: string
example:
phase: listen
heard: Can you book a meeting room for tomorrow morning
requestArgs:
conversationId: 65f0c0ffee0000000000abcd
responses:
'200':
description: The check's answer, or `ok:false` with an error.
content:
application/json:
schema:
type: object
properties:
ok:
type: boolean
done:
type: number
description: Probability (0–1) that the speaker is done (listen, end).
same:
type: number
description: >-
Probability (0–1) that a reply to `earlier` still answers
`heard` (drift, end).
interrupt:
type: number
description: >-
Probability (0–1) that the user is taking the turn
(barge).
react:
type: object
description: How the speaking twin should react (react).
properties:
cue:
type: string
enum:
- happy
- warm
- playful
- curious
- supportive
- concerned
- sad
- surprised
- angry
- distressed
- laughter
- none
description: >-
The most probable cue tag other than none; none when
`p` is under 0.2 (or, without per-tag probabilities,
when Jev chose none).
p:
type: number
minimum: 0
maximum: 1
description: >-
How strongly (0–1) a reaction is called for: 1 − Jev's
probability of none (without per-tag probabilities,
Jev's confidence in its cue, or 1 − it for none).
lookup:
type: object
properties:
kind:
type: string
enum:
- none
- knowledge
- web
- memory
- files
confidence:
type: number
ms:
type: number
error:
type: string
enum:
- 'off'
- react-off
- busy
- rate
- timeout
- error
- bad-input
- bad-answer
- bad-phase
description: >-
`react-off`: voice reactions are not on for this session
(react only).
examples:
answered:
value:
ok: true
done: 0.91
lookup:
kind: none
confidence: 0.88
ms: 240
reaction:
value:
ok: true
react:
cue: happy
p: 0.85
ms: 160
warm:
value:
ok: true
'off':
value:
ok: false
error: 'off'
'400':
description: >-
Malformed body (unknown phase, missing or non-string `heard` outside
`warm`, bad `specId`).
'401':
description: Unauthorized
security:
- apiKeyAuth: []
components:
securitySchemes:
apiKeyAuth:
type: apiKey
in: header
name: x-access-token
description: JWT token passed in x-access-token header
````
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.