AmiVoice logo

AmiVoice

by Advanced Media, Inc.
No reviews yet
Active1+ countriesCloudOn-premise
Quick facts
VendorAdvanced Media, Inc.
Year launchedN/A
StatusActive
LocationToshima, Tokyo, Japan
Countries served1+
Languages1
IntegrationsN/A
Free tierNO
Free trialNO
Contact salesYES

About AmiVoice

AmiVoice is the flagship AI speech recognition platform, dictation suite, and developer API engine developed by Tokyo-based Advanced Media, Inc.

AmiVoice is the flagship AI speech recognition platform, dictation suite, and developer API engine developed by Tokyo-based Advanced Media, Inc. Holding the leading market share for Japanese speech recognition for over two decades, AmiVoice converts human speech into highly accurate text across cloud APIs, dedicated enterprise servers, and offline mobile SDKs. Its primary strengths lie in its pre-trained, industry-specific vocabulary engines (tailored for medical EHRs, pharmaceuticals, finance, and insurance), its cost-efficient billing model that charges strictly for spoken segments rather than silent audio, and its integrated acoustic sentiment analysis and speaker diarization tools. For enterprise contact centers, healthcare providers, construction managers, and software developers seeking top-tier Japanese AI voice capabilities, AmiVoice provides a reliable, secure, and feature-rich digital foundation.

Pros & Cons

Pros
  • Enables secure, on-device voice processing for mobile apps without requiring an active internet connection.
  • Deep specialized recognition for Japanese medical, pharmaceutical, financial, and insurance terminology.
  • Billing charges accrue strictly during active speech, saving significant costs by ignoring silent pauses.
  • Exceptional accuracy in recognizing spoken Japanese, complex kanji pronunciations, regional dialects, and specialized jargon.
Cons
  • Acoustic sentiment analysis is available primarily via asynchronous HTTP batch processing.
  • Dedicated private servers and AWS PrivateLink connections involve higher setup and base fees.
  • Navigating dozens of specialized sub-products (VoXT, Ex7, Communication Suite, ACP API) requires initial guidance.
  • Non-Japanese language speech recognition features are less prominent than its core Japanese engines.

Features

Key features

Flexible On-Device Offline Operation (AmiVoice SDK)

Operates natively on mobile devices and local hardware without an internet connection, guaranteeing maximum privacy compliance.

Speaker Diarization & Filler Removal

Automatically identifies and labels different speakers without prior voice training while stripping out conversational filler words like "ah" and "um".

Integrated Acoustic Sentiment Analysis

Evaluates voice acoustics in real time to output 20 emotional parameters including joy, anger, stress, expectation, and dissatisfaction.

Pay-Only-For-Speech Billing Architecture

Calculates billing charges solely on detected spoken segments while filtering out and excluding silent pauses, reducing API runtime expenses.

Industry-Specific Specialized Acoustic Engines

Offers pre-trained speech models tailored specifically for medical terms, pharmaceuticals, finance, insurance, nursing care, addresses, and full name identification.

Additional features

Hands-Free PC & Device Voice Commands

Operates desktop applications, field inspection forms, and industrial equipment through custom voice commands.

Generative AI Integration (VoXT / ChatGPT)

Connects speech outputs directly to LLMs to automatically produce executive meeting minutes and summary reports.

Millisecond-Accurate Timestamping

Assigns precise millisecond timestamps to each utterance relative to audio start times for seamless media alignment.

Phonetic Katakana Output Display

Generates phonetic readings alongside text outputs, assisting downstream CRM matching and children's applications.

Automatic Inappropriate Language Masking

Filters out profanity and discriminatory language automatically during official business transcription.

Automatic Punctuation & Formatting

Automatically inserts full stops, commas, and question marks to convert raw speech into clean, structured text.

Custom Vocabulary & Word Registration

Allows users to register company-specific jargon, employee names, and proprietary product names easily via spelling and pronunciation inputs.

Pricing

Free trial
Free version
Request a quote
Promo Offer

Countries & Languages

1
Countries served
1
Interface languages
1
Billing currencies

Available in

Japan

Interface languages

Japanese

Billing currencies

🇯🇵JPY

No reviews yet

Be the first to drop a review

Alternatives to AmiVoice

FlexAI logo

FlexAI

FlexAI is an AI infrastructure orchestration platform designed to simplify access to computing resources for…

Tessl logo

Tessl

Tessl is an AI software development governance platform built for the AI-native era. It excels…

Lovable logo

Lovable

Lovable is an AI-powered full-stack app development platform for developers, founders, and creators.

ChatPDF logo

ChatPDF

ChatPDF is an AI-powered document analysis platform designed to help users interact with PDFs and…

ZARK logo

ZARK

ZARK is a risk management software from Bluedove that supports organizations in identifying and mitigating…

Intron EMR Platform logo

Intron EMR Platform

Intron EMR Platform is an electronic medical records software from Intron Health designed for healthcare…

Spot something wrong or outdated?

Suggest a correction — a reviewer verifies every change.

Often compared with AmiVoice

Compare any two tools →
FlexAI logo
FlexAI
Cloud Computing
0.0
Tessl logo
Tessl
IT infrastructure services
0.0
Lovable logo
Lovable
No Code Platform
0.0
ChatPDF logo
ChatPDF
Document Management
0.0