Sold by: Deepgram
Deployed on AWS
Free Trial
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the nova-3 model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0092/min as described by https://deepgram.com/pricing. Private pricing available upon request.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
Overview
Deepgram powers end to end voice solutions on AWS, from real time transcription to lifelike speech synthesis and interruptible, human like voice agents. Deploy our STT/TTS and agent runtime where you need them: In SageMaker, in a Deepgram managed Dedicated environment or self hosted inside your AWS VPC for maximum control and compliance, with native touchpoints to Amazon Bedrock and Amazon Connect to compose complete voice workflows.
Procure through AWS Marketplace to accelerate onboarding with usage based pricing and consolidated billing on your AWS invoice, ideal for trials, POCs, and scaling to production while aligning to AWS commitments.
Deepgrams AWS alignment includes the AWS Generative AI Competency and a multi year strategic collaboration, giving teams confidence that integrations, cosell, and global scale on AWS are first class.
Use cases include: real time contact center transcription and automation with Amazon Connect + Lex, Bedrock powered voice agents with Deepgram STT/TTS, and streaming/batch analytics via S3, API Gateway, Lambda, and EKS/EC2, all built on the AWS patterns your teams already trust.
Highlights
- Real time STT for human like conversations: Sub 300 ms streaming latency with industry leading accuracy (Nova 3: 6.84% median WER streaming; 5.26% batch) to keep pace with fast, noisy speech.
- Natural, low latency TTS: Sub 250 ms responses with lifelike speech and streaming delivery for natural turn taking in real time.
- Production ready voice agents on AWS: Combine Deepgram STT/TTS with Amazon Bedrock for reasoning and Amazon Connect and Lex for contact center workflows supporting interruptible, human like dialogs at scale alongside real time STT voice agents and real time STT for transcription.
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
Free trial
Try this product free for 14 days according to the free trial terms set by the vendor.
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 |
|---|---|---|
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $3.90/host/hour |
inference.count.m.i.c Inference Pricing | inference.count.m.i.c Inference Pricing | $0.001/request |
Dimensions summary
You pay based on usage, with two dimensions that work together. The first charges by the hour for model inference running on an ml.m5.xlarge instance in batch mode. This covers the compute time your deployed endpoint stays active. The second charges per inference request processed. So your cost combines the hours your instance runs plus the number of transcription requests you send. You deploy the model on a SageMaker endpoint and route audio to it. There is no upfront commitment; billing follows what you actually use.
Top-of-mind questions for buyers
The hourly charge covers the compute time your deployed SageMaker endpoint stays active on the ml.m5.xlarge instance in batch mode. You accrue charges for every hour the endpoint runs, whether or not you send audio. Asynchronous endpoints can scale to zero when no requests are queued, stopping compute charges during idle periods.
Both charges apply at the same time. You pay for every hour the endpoint runs, plus a charge for each inference request processed. For steady, high-volume transcription, request counts add up alongside continuous instance-hours. For occasional use, instance-hours can dominate if the endpoint stays running between requests.
Synchronous batch requests to a real-time endpoint are capped at 25 MB per request body. For larger files up to 1 GB, use an asynchronous endpoint, which writes results to Amazon S3 and can scale to zero when idle. Each request you process counts toward the per-request charge.
developers.deepgram.com
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
Additional details
Inputs
- Input MIME type
- audio/*, *
https://github.com/deepgram-devs/dg-sagemaker
NOT SUPPORTED
Resources
Support
Vendor support
Basic support is provided through email (aws@deepgram.com ). Premium and VIP support packages are also available for enterprise clients.
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
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the nova-3 model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0077/min as described by https://deepgram.com/pricing. Private pricing available upon request.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the aura-2 model which can each speak a set of languages and voices. See version details for more information. Deepgram charges are billed per request as described by https://deepgram.com/pricing
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the flux model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0078/min as described by https://deepgram.com/pricing.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
Deepgram is the enterprise Voice AI platform for building and scaling real time voice applications on AWS. This product listing contains multiple versions of the flux model which can each transcribe a set of languages. See version details for more information.
You will be billed $0.0077/min as described by https://deepgram.com/pricing. Private pricing available upon request.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker Bi-Directional Streaming API. Additional native touchpoints with Amazon Bedrock, Lex, and Amazon Connect make it simple to compose full voice experiences with the cloud services your teams already trust.
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.