Guardrails API

The Guardrails API adds safety, privacy, and compliance controls to AssemblyAI transcripts and audio. It covers PII redaction in both transcript text and the underlying audio, profanity filtering, and content moderation, applied as add-ons to a transcription request.

General
Developer	AssemblyAI
Type	Safety and compliance API
License	Commercial API
Documentation	assemblyai.com/products/guardrails

Core Features

PII text redaction: removes personally identifiable information from transcript text.
PII audio redaction: redacts personally identifiable information directly in the audio file.
Profanity filtering: filters profane language out of transcript output.
Content moderation: flags or filters unsafe or policy-violating content.

Pricing

Guardrails features are billed as add-ons on top of the base Speech-to-Text rate:

Add-on	Rate
Profanity Filtering	+$0.01/hour
PII Text Redaction	+$0.08/hour
Content Moderation	+$0.15/hour

Source: assemblyai.com/pricing

Use Cases

Regulated industries: healthcare and financial services use cases that require PII redaction before storing or sharing transcripts.
Customer support and contact centers: content moderation and profanity filtering on recorded or live calls.
Compliance workflows: redacting sensitive information from audio archives before retention or sharing.

Ecosystem and Integrations

Guardrails add-ons apply to output from both Speech-to-Text and Universal-Streaming, and can be combined with Speech Understanding add-ons on the same request.

Read the Guardrails docs to add safety and compliance controls to an existing transcription request.

NURDA6FOOT4

SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf SDSADASDDASDSADASD ka dwkec keCJWeofweokMsdcosmks slnl;seNCVL;wenvipuwernfuiwnwoerf

HandSpeak

SignBridge is a real-time AI-powered sign language interpretation system designed to make communication more accessible between sign language users and people who do not understand sign language. Using a camera, the system detects hand and body movements, analyzes gesture sequences, and converts recognized signs into natural-language text and speech. The project will leverage AMD GPU acceleration to improve real-time computer vision and AI inference performance, allowing the system to process video with low latency. Beyond individual signs, SignBridge aims to recognize sequences of gestures and reconstruct meaningful phrases, making communication more natural. The project combines accessibility, computer vision, AI, and high-performance AMD computing to create a practical assistive technology solution.

OmniCaption

OmniCaption AI: Universal Real-Time System Audio Captions for Linux OmniCaption AI is a system-wide, application-agnostic live captioning HUD built specifically for GNOME and Linux environments. Unlike app-bound caption tools limited to specific browsers or meeting platforms, OmniCaption AI intercepts all system-level output audio directly at the kernel audio layer using PipeWire. Whether you are participating in a Discord call, attending a Twitter/X Space, streaming a video on a web browser, or joining a remote Zoom meeting, OmniCaption AI captures the incoming sound and delivers instantaneous visual captions. Powered by AssemblyAI’s real-time speech-to-text infrastructure, OmniCaption AI streams raw audio over low-latency WebSockets to produce sub-second, highly accurate transcriptions. Local Voice Activity Detection (Silero VAD) filters out silence to optimize network bandwidth and ensure instantaneous response times. Transcripts are displayed on an always-on-top, translucent PySide6 overlay window designed to fit seamlessly into modern GNOME Wayland and X11 workflows without disrupting active user focus or application input. Beyond real-time captioning, OmniCaption AI features a local web dashboard that communicates with a background FastAPI daemon. This dashboard allows users to manage custom vocabulary prompts for domain-specific technical terminology, review and search past call session transcripts stored securely in a local SQLite database, and customize HUD visual parameters like font scaling, text color, and window opacity. OmniCaption AI provides an essential, privacy-conscious accessibility layer for deaf, hard-of-hearing, and non-native speakers across the entire Linux desktop ecosystem.

Task Voice Agent

Voice Task Assistant is a practical productivity voice agent built entirely on AssemblyAI’s Voice Agent API. Users speak naturally to capture tasks, review their list, and mark items complete — without touching a keyboard. The entire voice stack (speech-to-text with Universal-3 Pro, LLM reasoning, and text-to-speech) runs through a single AssemblyAI connection with natural turn-taking and barge-in support. Replies are kept short and direct so the interaction feels fast and useful. This project demonstrates a clean, production-ready use of the Voice Agent API for everyday personal productivity. It requires no extra services for the core experience and can be extended later with HTTP tools for persistent storage.

Echo — Voice-First Shopping Assistant

Echo reimagines online shopping as a conversational experience for blind and low-vision users. Instead of navigating visually dense product pages, users can simply speak to Echo to discover products, compare prices and ratings, ask how a product looks, add items to their cart, apply coupons, and complete checkout. Echo is designed around accessibility from the beginning, with voice interaction, screen-reader support, and minimal dependence on pointer-based navigation. Product appearance is represented through structured information such as colors, patterns, fit, sleeves, neckline, texture, and overall style, allowing the assistant to describe products without inventing visual details. Behind the conversation, Echo uses AssemblyAI for real-time voice interaction, an LLM with tool calling, and an Express + MongoDB backend that validates every shopping action. The AI can request an action, but the backend confirms whether it actually happened. Checkout also requires explicit user confirmation. The result is a shopping experience built around conversation rather than visual navigation — making discovery, decision-making, and purchasing accessible through a natural voice interaction.

ClaimDeskAI

The product should feel less like a chatbot and more like an enterprise verification operating layer. A user asks a question by voice, ClaimDeskAI gathers permitted evidence, executes calculations in isolated containers, uses organizational memory for context, identifies contradictions, and returns an answer with a complete audit trail. Core product workflow Voice question → understand claim → retrieve evidence → run verification → calculate → compare → explain → show sources → save case → update organizational memory ClaimDeskAI doesn't merely answer enterprise questions—it proves where the answer came from, calculates it reproducibly, remembers organizational context safely, and refuses to claim certainty when the evidence is incomplete.