OpenAI Whisper Applications

Browse applications built on OpenAI Whisper technology. Explore PoC and MVP applications created by our community and discover innovative use cases for OpenAI Whisper technology.

KindredRelay: Keeping Families Connected

KindredRelay turns hospital recordings, document photos and family updates into a shared timeline, with answers linked to original sources and questions for the care team, so families can stay informed and share the care.

CareRelay

Anthropic ClaudeDeepSeek V3Whisper+3

DubGuard: Evidence Backed Narration Review

DubGuard spots potentially dangerous changes in recorded industrial instructions such as off becoming on using local speech recognition, protected rule checks, AMD DeepSeek analysis, audio-linked evidence, and human review.

Noone

Token FactoryWhisperDeepSeek V3

CLARIO

CLARIO turns years of scattered symptoms and medical records into a clear story for doctors. Powered by AMD AI, it combines specialized models, rare-disease knowledge, and human oversight to help patients be heard sooner - without replacing clinicians.

Revived

AMD Developer CloudDeepmindGemma+3

SayAgain — catches wrong radio read-backs

On plant radio, a wrong read-back can close the wrong valve. SayAgain flags it for the shift supervisor: a model on the AMD Token Factory points at the words, code decides. 89 scripted exchanges: 0 wrong read-backs passed; an LLM judge passed 2.

Edy Team

GemmaQwen3Whisper+2

PaperOps – The Glove-Proof Industrial Dispatcher

A technician holds one button and describes a machine fault by voice. Gemma 4 on AMD GPUs understands the report; PaperOps checks the manual and stock and prints a repair ticket: safety step first, the right part, its exact shelf. No screen, no typing.

ZOZ INNOVATIONS

Token FactoryGemmaDeepmind+3

AXONFAS: Clinic-Supervised Home Physiotherapy

Home physiotherapy your clinic can actually see: the browser camera tracks each exercise, counts only well-done reps and flags unsafe compensations in real time, while the physiotherapist follows live and sets the plan.

AXONFAS

AMD Developer CloudAMD ROCmWhisper+1

PatientKeeper Retorno

Doctor-centered follow-up with accountable next steps, source review and simulated contacts. Local Gemma via AMD Token Factory + Evolus returned a cited administrative candidate; the public demo preserves recorded evidence and human control.

FIGUEIRA AI

AMD ROCmAMD Developer CloudCodex+3

SnapSell

SnapSell turns narrated inventory videos into reviewed resale listings, researches evidence-backed asking prices, prepares marketplace listing kits, and helps sellers manage buyer replies, pickups and recorded sales with AMD-powered AI.

MTKulsary

CodexAMD Developer CloudAntigravity+4

Firefly Voice Companion

Firefly is a memory-powered AI voice companion evolved from a desktop AI pet project, combining AssemblyAI voice technology, intelligent agents, and long-term memory to provide natural and personalized human-AI conversations.

Fuyong AI Lab

OpenAIQwen3-CoderWhisper+1

Voice-Driven Test & Debugging Swarm

An autonomous QA swarm that triggers hybrid Java test suites via voice command, captures failures from Surefire XML reports, hands them to IBM Bob 2.0 for root-cause analysis, and plays the fix summary aloud via ElevenLabs TTS.

Hal Jordan

IBMElevenLabsWhisper

JARVIS AI – Agentic Computer Automation

JARVIS AI is an agentic AI automation system that converts natural-language commands into verified computer actions using intelligent planning, tool orchestration, browser automation, desktop control, memory, and built-in safety mechanisms.

Ultron

AntigravityAnthropic ClaudeChatGPT+5

MindBridge: AI Mental Health Support

MindBridge is a compassionate mental-health platform that helps users understand their emotions, complete screenings, receive supportive guidance, find nearby professionals, and access emergency assistance when urgent help is needed.

Infinite Horizon

AI/ML APIAntigravityBERT+5

Legal-Voice – Voice Legal Forms

Legal-Voice helps people complete legal forms by speaking naturally in their preferred language. AI turns their answers into structured form data, guides them through the required fields, and generates a ready-to-review legal document.

AI Team

GPT-4LangChainLLaMA+13

Foreman - Natural-Language Edge AI Inspector

Foreman turns spoken or typed inspection rules into real-time PASS/FAIL/UNCLEAR decisions using SiMa.ai Modalix, object detection, temporal evidence, and Qwen3-VL 4B - without retraining the vision stack.

XXI

SiMa Modalix MLSoCQwen3Whisper

Robin Voice Ops

Voice operations agent for home-services businesses — books jobs, checks availability, gives order status, and routes approvals to a human dispatcher, with hash-chained audit logs and caller memory. Deep AssemblyAI Voice Agent API integration.

Robin Voice Ops

Whisper

VERA — Voice AI for Business

VERA is a voice-first AI assistant that combines natural conversation, business knowledge, maps, visual explanations, workflows, and Gmail-powered support to turn questions into useful real-world actions.

Vexora

AI/ML APIAnthropic ClaudeChatGPT+5

Recall — Test understanding, not memory.

Recall is an AI learning companion that helps students strengthen understanding by making them explain concepts, challenging weak reasoning, identifying misconceptions, and adapting questions to their individual knowledge gaps.

Monk

AMD Developer CloudAnthropic ClaudeCodex+7

FlexiMind: Autonomous AI Workflow Orchestrator

An AMD-powered multi-agent orchestration platform that turns user goals into executed workflows by planning tasks, routing them to specialized AI agents, using tools, verifying results, and automatically recovering from failures.

Bliss AI Labs

AI/ML APIAntigravityWhisper+5

Sabaq: Voice Tutor for Urdu-English Classrooms

Sabaq makes mixed Urdu-English lectures searchable by restoring technical terms that speech-to-text writes inconsistently, then adds transcript-based voice Q&A. In our tests, searchable term recall rose from 16% to 79% for new speakers.

Code Switch

StreamlitGemini AIGroq+1

Second Chair

Every voice agent assumes two people in the room. Second Chair is built for three: it knows who is speaking, warns the professional privately when they cross a regulatory line, and stays silent unless addressed by name.

Enigma Pro

GroqAssistants APIAnthropic Claude+2

Speech-to-Maya

A local, voice-driven AI copilot for Autodesk Maya that streams real-time speech via AssemblyAI WebSockets and translates intent into procedural 3D Python code using Ollama and Qwen 2.5.

VoiceAgentJ

Qwen3-CoderWhisper

Memory Mate

Memory Mate is an AI native care companion that gently answers seniors' repeated questions using real family updates, easing caregiver burnout for those supporting loved ones with memory loss or early stage dementia.

Side quester

OpenAIAntigravitySpeechmatics api+4

Video Captioner

Vision-based video captioning pipeline using Gemma 4 31B. Analyzes video frames,nbuilds scene understanding, generates 4 caption styles with automatic quality scoring.

CrazyCherry

AI/ML APIWhisperGemma+1

TruLens-by Mithridates

TruLens is a real-time AI overlay that listens to live media streams, instantly transcribes speech, and surfaces context-aware fact-checks directly to your screen to combat misinformation on the fly.

Mithridates

AMD ROCmAntigravityAMD Developer Cloud+5

Emergency Smart Dispatcher

AI-powered emergency dispatch for Thailand's 191: live Thai transcription (Whisper), DeepSeek triage via Fireworks AI, location from speech alone (RAG landmarks, no GPS), one-click dispatch to the exact zone officer. Validated on AMD Instinct MI300X.

emergency-smart-dispatcher

AMD ROCmWhisperDeepSeek V3

ReachIQ AI - Competitive Intelligence Engine

ReachIQ AI's Video RAG engine ingests competitor YouTube videos, builds a vector knowledge base, and generates strategic competitive intelligence reports — powered by Gemma 3 4B running natively on AMD Developer Cloud via ROCm + vLLM.

InstinctAgent

AI/ML APIAMD ROCmGemma+5

ClipContext

Upload a clip. Get the top 5 titles, descriptions, and hashtag sets — picked by an AI discriminator from 10 independently generated candidates per category, grounded in what your video actually says and shows and whats currently trending on youtube.

Kira

AMD Developer CloudWhisperAI/ML API

Persona Studio AI

PersonaStudio AI maps a video's core meaning via text transcription or Gemma 4 vision into a reusable "Content DNA" payload. Users can instantly transform this single blueprint into multi-platform content without ever re-analyzing the video.

Trionda

AMD ROCmAMD Developer CloudGroq+2

AuraCaptioner: Grounded Multi-Style Captions

Two-stage video captioning agent: Chain-of-Verification grounding feeds four distinct-tone captions, with a self-judge regeneration pass and a fail-safe pipeline that guarantees valid, complete output on every run, even under model or infra failure.

AuraStorm

WhisperAntigravityAnthropic Claude+2

AITinerary

Turn any travel idea into a complete trip. AITinerary uses AI to convert your preferences and Instagram/YouTube inspiration into personalized itineraries, hidden gems, budget planning, recommendations, and an intelligent travel companion.

Ctrl-C*Ctrl-V

AI/ML APIOpenAIAssistants API+16

30apps loaded