Overview
AmiVoice API - Developer Speech Recognition Engine
AmiVoice API is a speech-to-text API that converts audio into text with high accuracy. Send audio to the API endpoint and receive transcribed text results. Build meeting transcription tools, voice-controlled applications, contact center solutions, and more.
Key Capabilities
-
Real-Time Transcription (WebSocket and Synchronous HTTP): Process audio streams and short utterances in real time for live captioning, voice-controlled IoT devices, phone auto-response systems, and contact center call monitoring.
-
Batch Transcription (Asynchronous HTTP): Process large audio files in batch mode for transcribing call recordings, meeting recordings, and archived video content.
-
Industry-Specific Engines: Choose from general-purpose engines or specialized engines optimized for medical, insurance, financial, and other industry terminology to significantly improve recognition accuracy.
-
Speaker Diarization: Identify and label multiple speakers in audio without prior training, making it easy to distinguish who said what in multi-party conversations.
-
Emotion Analysis: Analyze speaker emotions from audio and output 20 parameters including joy, anger, stress, dissatisfaction, and expectation approximately every 2 seconds. Powered by ESAS technology developed from 3 million audio source validations.
-
Custom Dictionary Registration: Register product names, proper nouns, company-specific terminology, and personal names to improve recognition accuracy for your specific use case.
-
Automatic Punctuation and Filler Removal: Punctuation marks and question marks are automatically added to results. Filler words like "um" and "uh" are automatically removed (configurable).
-
Reading (Furigana) Output: Recognition results include estimated readings, useful for children's applications and CRM or database system integration.
-
Profanity Filtering: Inappropriate terms are automatically filtered from transcription results for professional business use.
AWS Integration
- AWS PrivateLink Support: Connect to AmiVoice API through AWS PrivateLink without traversing the public internet. Create a VPC endpoint in your Amazon VPC to access the speech recognition API from within the AWS network. No internet gateway, NAT Gateway, or public IP address required. Available for both synchronous and asynchronous APIs as separate options.
Automatic Learning System
The general conversation engine is continuously updated through an Automatic Training System (ATS), ensuring recognition of newly emerging words and terminology without manual intervention.
Supported Languages
- Japanese
- Chinese
- Multilingual options
Use Cases
- Contact center call transcription and analysis
- Meeting minutes and transcription
- Voice-controlled smartphone apps and embedded devices
- IoT device voice commands
- Phone auto-response systems
- Medical documentation and pharmacy communication tools
- Municipal government transcription services
- Voicebot and voice assistant development
Recognition Modes
- End-to-End engine for latest performance
- Hybrid engine with selectable language and acoustic models for industry-specific needs
AmiVoice API handles all development and service delivery in-house, ensuring direct technical support from engineering staff for API integration and ongoing operations.
Highlights
- Industry-specific speech recognition engines deliver high accuracy for medical, insurance, financial, and general-purpose use cases. Custom dictionary registration allows you to add product names, proper nouns, and company-specific terminology. The Automatic Training System continuously updates engines with newly emerging words, ensuring recognition stays current without manual intervention.
- Real-time transcription via WebSocket and synchronous HTTP for live applications like contact centers, voice-controlled devices, and phone auto-response systems. Batch transcription via asynchronous HTTP handles large audio files for meeting recordings, call archives, and video content. Speaker diarization identifies and labels multiple speakers without prior training.
- AWS PrivateLink connectivity lets you access AmiVoice API from within your Amazon VPC without traversing the public internet - no internet gateway, NAT Gateway, or public IP required. Emotion analysis outputs 20 parameters including joy, anger, stress, and expectation approximately every 2 seconds, powered by ESAS technology validated against 3 million audio sources.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Cost/month | Overage cost |
|---|---|---|
General Engines (No Logging) - 10 Hours Free | $0.00 | |
General Engines (No Logging) - For Private Offer | $0.00 |
The following dimensions are not included in the contract terms, which will be charged based on your usage.
Dimension | Cost/unit |
|---|---|
General Engines (No Logging) - Additional 1 sec | $0.000375 |
General Engines (Logging) - Additional 1 sec | $0.00025 |
General Engines (Asynchronous) (No Logging) - Additional 1 sec | $0.00025 |
General Engines (Asynchronous) (Logging) - Additional 1 sec | $0.0002 |
Medical Engines (No Logging) - Additional 1 sec | $0.0005625 |
Medical Engines (Logging) - Additional 1 sec | $0.000375 |
Domain-Specific Engines (No Logging) - Additional 1 sec | $0.000375 |
Domain-Specific Engines (Logging) - Additional 1 sec | $0.0003 |
Sentiment Analysis - Additional 1 sec | $0.0004 |
Dimensions summary
Top-of-mind questions for buyers
Vendor refund policy
For refund policy, see AmiVoice API - SLA 2.4
Custom pricing options
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
AmiVoice provides free technical support for API integration and ongoing operations. Technical inquiries are handled directly by engineering staff who develop and maintain the speech recognition engines.
Support Includes:
- Technical assistance during API implementation
- Troubleshooting for individual issues after deployment
- Free one-on-one online consultation sessions with dedicated staff
- Technical support form
Resources Available:
- Technical documentation
- Service introduction webinars
- Downloadable comparison materials and service guides
All technical support is provided at no additional cost. For inquiries, use the contact form available through the AmiVoice Cloud Platform portal.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
