Sold by: Smallest AI
Deployed on AWS
Whole-file English transcription with speaker diarization and PII/PCI redaction; runs on Batch Transform, Async and real-time inference; fully network-isolated so audio never leaves the account.
Overview
Pulse Batch by Smallest AI transcribes complete recordings at high throughput: 25 seconds of audio in under 0.2 seconds on a single L4. Send a file to the real-time endpoint, queue it through Asynchronous Inference, or run whole S3 prefixes through Batch Transform; the same container serves all three. Pulse Batch includes speaker diarization, word-level timestamps, keyword boosting, punctuation, inverse text normalization, and built-in PII/PCI redaction. It runs with network isolation enabled, so audio and transcripts stay inside your AWS account. For live audio, see Smallest AI Pulse Speech-to-Text Streaming.
Highlights
- High-throughput whole-file transcription: hundreds of times faster than real time on a single ml.g6 instance.
- Speaker diarization, word-level timestamps, keyword boosting and built-in PII/PCI redaction in one call.
- One container for real-time, Async and Batch Transform; network-isolated, so audio never leaves your account.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.g6.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.2xlarge instance type, real-time mode | $10.00 |
ml.g6.2xlarge Inference (Batch) Recommended | Model inference on the ml.g6.2xlarge instance type, batch mode | $10.00 |
ml.g6.4xlarge Inference (Real-Time) | Model inference on the ml.g6.4xlarge instance type, real-time mode | $10.00 |
Dimensions summary
You pay by the hour for the compute instance that runs the speech-to-text model. Pricing scales with two factors: instance size and processing mode. Two instance sizes are offered, ml.g6.2xlarge and ml.g6.4xlarge, with the larger instance carrying more compute capacity. For processing mode, you can choose real-time inference, which handles live streaming audio, or batch inference, which processes recorded audio files. Real-time mode is available on both instance sizes. Batch mode is offered on the ml.g6.2xlarge instance. You are billed for each host hour the instance runs.
Top-of-mind questions for buyers
A host hour is one hour that the chosen compute instance runs, regardless of how much audio you process during that hour. You pay for the instance's running time, not per minute of audio or per transcript. Billing accrues while the instance is active.
Real-time mode handles live streaming audio and is offered on both instance sizes. Batch mode processes recorded audio files and is offered on the ml.g6.2xlarge instance. Both meter by host hour. Your cost depends on which mode and instance you run, and how long it stays active.
Charges apply per host hour while the instance runs. A fully stopped instance does not accrue software host-hour charges. Underlying AWS infrastructure fees, such as storage, may still apply to stopped instances separately from the model's host-hour metering.
www.smallest.ai
Helpful?
Vendor refund policy
N/A
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Whole-file English transcription.
- POST /invocations with a complete recording; the same container also serves Asynchronous Inference and Batch Transform unchanged.
- Speaker diarization: request diarize=true; each word and utterance carries a speaker label.
- Word-level timestamps, keyword boosting, punctuation, inverse text normalization, and built-in PII/PCI redaction (redact_pii=true, redact_pci=true).
- Requests up to 100 MB.
- Runs with network isolation enabled: no outbound network access, so your audio stays inside your AWS account.
Requires an Ada-generation GPU (ml.g6) for both real-time and batch.
Additional details
Inputs
- Summary
audio/wav, audio/x-raw, application/octet-stream or application/json; English
- Input MIME type
- audio/wav, audio/x-raw, application/octet-stream, application/json
https://docs.smallest.ai/models/api-reference/speech-to-text/speech-to-text
https://docs.smallest.ai/models/api-reference/speech-to-text/speech-to-text
Support
Vendor support
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
bidirectional-WebSocket streaming; diarization and PII redaction built in; fully network-isolated so audio never leaves the account.
Real-time, 44.1 kHz text-to-speech with bidirectional-WebSocket streaming; fully network-isolated so text and audio never leave the account.
Smallest AI's Voice AI Platform brings our entire voice stack to AWS Marketplace under one listing with consolidated billing. Build and deploy no-code Atoms voice and chat agents that automate support, sales, and operations with end-to-end conversation handling in 20+ languages, or procure the underlying models directly: Lightning text-to-speech (broadcast-quality 44.1 kHz audio, ~100 ms latency, instant voice cloning, 15 languages) and Pulse speech-to-text (~64 ms first transcript, diarization, PII/PCI redaction, 38 languages). Subscribe once, use any mix of agents, TTS, and STT, and see all usage on a single AWS invoice with usage-based pricing. Enterprise-grade latency, SOC 2 Type II and PCI-DSS, flexible AWS-region deployment with data residency and in-VPC options, and private offers for committed-use deals.
Smallest Atoms is a platform for deploying hyper-realistic AI agents that can talk to anyone on voice or text, in any language and any voice. Atoms act like AI employees that handle end-to-end workflows across support, sales, and operations, using your business context, tools, and data. They can automate conversations such as answering queries, collecting information, completing transactions, and triggering downstream actions, while continuously learning from mistakes. Atoms integrate into your stack via SDKs and APIs, making it easy for teams to embed real-time, natural conversations into web, mobile, and backend systems.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.