Overview
NamisenseAPI is a speech-to-text API from NamiTech for contact centers, call analytics and voice applications. Your subscription includes two APIs: real-time transcription and batch transcription. Each API has its own API key and its own usage dimension.
Real-time transcription (ASR Streaming): your application streams audio over a secure WebSocket on port 443. The service sends the final transcript of each phrase when the speaker pauses. Send raw 16-bit PCM audio, mono, at 8 kHz or 16 kHz. For a phone call, open one session for the agent channel and one for the customer channel. The service stores the hold periods of the call with the session. Gender detection (Beta) is also available.
Batch transcription (ASR Long-form): your application uploads a recording over HTTPS, submits a job, and gets the result by callback or by polling. A recording can be up to 4 hours long, mono or stereo, in MP3, MP4, WAV, OPUS, WebM, M4A, OGG or most other common audio and video formats. The result is a JSON file with timestamped segments. Speaker diarization has use cases for calls and interviews, for meetings with more than 4 speakers, and for field recordings in noisy places. Speaker identification names the speakers from your reference recordings. Agent detection labels each segment as agent or customer, from the channel of a stereo call or from the transcript.
Both APIs give punctuated and normalized transcripts, with these options: phrase boosting for product names and domain terms (Japanese, English and Vietnamese); a custom dictionary that replaces recognized words with your own spelling; PII detection and masking for Japanese and Vietnamese (phone numbers, card numbers, addresses, personal names, ID numbers and more); sentiment and emotion analysis for each segment; and phoneme output (Beta) for Japanese, with katakana readings and timestamps.
Languages: Japanese, English, Vietnamese, Thai, Indonesian, Malay and Arabic (Beta). The available features depend on the language.
Processing: NamiTech's own speech engines process the audio. One exception: sentiment analysis for a language other than Japanese and Vietnamese can send the text of each segment to an external AI provider through the NamiTech gateway. Batch transcription processes the audio and stores the results in Japan (AWS ap-northeast-1).
Getting started: after you subscribe, register on the NamiTech Business Portal. You get one API key for real-time transcription and one for batch transcription. The documentation has runnable code samples in Python and JavaScript for both APIs, and in cURL for batch transcription.
Pricing: Pay as you go, per minute of audio processed, with separate prices for real-time and batch transcription. There is no minimum commitment. Usage is aggregated hourly and rounded up to the next whole minute. For custom pricing and volume discounts based on usage commitments, please contact api-admin@namitech.io .
Highlights
- Real-time streaming over WebSocket and batch transcription of recordings up to 4 hours, with diarization, PII masking, sentiment and emotion, and phrase boosting.
- Built for Japanese; also English, Vietnamese, Thai, Indonesian, Malay and Arabic (Beta) are available.
- Pay per audio minute with no minimum commitment; volume discounts available for committed usage, please contact api-admin@namitech.io.
Details
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/unit |
|---|---|---|
Real-time transcription minutes | Minutes of audio processed by the real-time (WebSocket) speech-to-text API. | $0.002 |
Batch transcription minutes | Minutes of audio processed by the batch (long recording) speech-to-text API. | $0.004 |
Vendor refund policy
Usage fees are billed per minute of audio processed and are non-refundable once the usage has been metered. If you believe you were billed in error, contact contact@namitech.io within 30 days of the charge; Nami Technology Japan Co., Ltd. will review the request and issue a refund where the error is confirmed.
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.
Resources
Vendor resources
Support
Vendor support
NamiTech provides onboarding and technical support for NamisenseAPI Monday through Friday, 09:00-18:00 JST, excluding Japanese public holidays. Contact us by email at api-admin@namitech.io or through https://www.namitech.io/contact . The API documentation, with code samples, is on the NamiTech Business Portal. The sandbox is available after sign-up.
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

