Sold by: Gradium
Deployed on AWS
Gradium builds the technological backbone, models and infrastructure, to support all voice applications. We work at the finest level of details to design natural, expressive, real-time voice interactions at scale.
Overview
We provide real-time Text to Speech and Speech to Text models in English, French, German, Spanish and Portuguese, instant voice cloning and much more.
Highlights
- Real time
- Highly expressive
- 5 languages
Details
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.m5.large Inference (Batch) Recommended | Model inference on the ml.m5.large instance type, batch mode | $0.00 |
ml.g6e.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.xlarge instance type, real-time mode | $12.00 |
ml.g5.xlarge Inference (Real-Time) | Model inference on the ml.g5.xlarge instance type, real-time mode | $12.00 |
ml.g5.2xlarge Inference (Real-Time) | Model inference on the ml.g5.2xlarge instance type, real-time mode | $12.00 |
ml.g5.4xlarge Inference (Real-Time) | Model inference on the ml.g5.4xlarge instance type, real-time mode | $12.00 |
ml.g5.8xlarge Inference (Real-Time) | Model inference on the ml.g5.8xlarge instance type, real-time mode | $12.00 |
ml.g5.12xlarge Inference (Real-Time) | Model inference on the ml.g5.12xlarge instance type, real-time mode | $12.00 |
ml.g5.16xlarge Inference (Real-Time) | Model inference on the ml.g5.16xlarge instance type, real-time mode | $12.00 |
ml.g5.24xlarge Inference (Real-Time) | Model inference on the ml.g5.24xlarge instance type, real-time mode | $12.00 |
ml.g5.48xlarge Inference (Real-Time) | Model inference on the ml.g5.48xlarge instance type, real-time mode | $12.00 |
Dimensions summary
You pay by the hour for the AWS SageMaker instance you run, billed per host hour (HostHrs). Pricing scales with the instance type and size you choose, not with audio volume. One option covers batch inference on an ml.m5.large instance. The rest cover real-time inference across GPU instance families (g4dn, g5, g6, g6e, g7, g7e, p3, p4d) in sizes from xlarge up to 48xlarge. Larger sizes within a family provide more compute. You select the instance that fits your throughput and latency needs, and billing follows your running hours.
Top-of-mind questions for buyers
One host hour is one hour that a single SageMaker instance runs the model. You are billed for each running instance per hour of uptime. The charge reflects the compute you reserve, not the amount of audio you generate or the number of requests you send.
Charges accrue only while an instance is running and serving the model. A fully stopped instance stops the host-hour software charge. Underlying AWS infrastructure costs, such as storage, may still apply separately. The software meters running time, not audio volume.
Both bill per host hour. The ml.m5.large batch option processes queued requests without a persistent endpoint, suited to bulk, non-interactive jobs. The GPU real-time options keep an endpoint live for streaming, low-latency speech, suited to interactive voice agents. You choose based on workload type.
gradium.ai
Helpful?
Vendor refund policy
No refund policy
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
Validated Gradium real-time text-to-speech model update.
Additional details
Inputs
- Summary
Bidirectional streaming for real-time inference
- Input MIME type
- application/json, application/octet-stream
{"type":"text","text":"foo"}
Not applicable
Resources
Vendor resources
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
Gradium builds the technological backbone, models and infrastructure, to support all voice applications. We work at the finest level of details to design natural, expressive, real-time voice interactions at scale.
A voice AI platform delivering real-time Text-to-Speech, Speech-to-Text, and instant voice cloning through streaming WebSocket APIs. Build low-latency voice agents in English, French, German, Spanish, and Portuguese with a single API key.
Turn claims, tickets, and incidents into a searchable memory using Aurora PostgreSQL and pgvector, with optional AI root-cause suggestions.
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.
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.