Sold by: Deepgram
Deployed on AWS
Free Trial
Deepgram Voice AI Flux delivers industry-leading multilingual speech-to-text transcription with real-time streaming via Amazon SageMaker. Powered by Deepgram's Flux model, this product provides high-accuracy transcription across multiple languages with ultra-low latency.
Overview
Deepgram Voice AI Flux Multilingual Speech-to-Text (STT) Streaming enables real-time, high-accuracy transcription across multiple languages using Amazon SageMaker's bidirectional streaming inference. Built on Deepgram's state-of-the-art Flux model, this product delivers low-latency speech recognition ideal for live captioning, voice assistants, call center analytics, and customer experience applications.
Deployment is straightforward through Amazon SageMaker endpoints. Customers run real-time inference using SageMaker bidirectional streaming APIs, enabling seamless integration into existing applications and workflows with minimal friction.
The Flux model supports multilingual transcription, allowing businesses to serve global audiences with a single unified solution. With Deepgram's proven AI infrastructure, customers benefit from enterprise-grade reliability, performance, and accuracy across a broad range of languages and acoustic environments.
Highlights
- Real-time multilingual speech-to-text transcription powered by Deepgram's state-of-the-art Flux model via Amazon SageMaker streaming inference
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/host/hour |
|---|---|---|
ml.m5.xlarge Inference (Batch) Recommended | Model inference on the ml.m5.xlarge instance type, batch mode | $37.00 |
ml.g6.2xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6.2xlarge instance type, real-time mode | $51.80 |
ml.g6e.2xlarge Inference (Real-Time) | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $74.00 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $37.00 |
ml.g4dn.2xlarge Inference (Real-Time) | Model inference on the ml.g4dn.2xlarge instance type, real-time mode | $51.80 |
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
Added Flux Multilingual model support for streaming speech-to-text transcription across multiple languages.
Additional details
Inputs
- Summary
Audio for transcription
- Input MIME type
- audio/*, *
Audio bytes payload
Audio bytes payload
Support
Vendor support
For product support, visit https://deepgram.com/support or email support@deepgram.com . Documentation and sample notebooks are available at https://github.com/deepgram-devs/dg-sagemaker . Enterprise support options are available for SageMaker deployments.
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 model transcribes the following 10 languages at once, allowing for aggressive code switching during the conversation.
English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch.
Our APIs for Nova Speech to Text (STT) are natively available in the new SageMaker BiDirectional 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. Our APIs for Nova are natively available in the new SageMaker BiDirectional 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. Our APIs for Flux are natively available in the new SageMaker BiDirectional 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 model is training on a wide corpus of English medical conversations. Our APIs for Nova are natively available in the new SageMaker BiDirectional 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. Our APIs for Nova are natively available in the new SageMaker BiDirectional 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.