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 | $12.00 |
ml.g6e.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.xlarge instance type, real-time mode | $3.07 |
ml.g6e.2xlarge Inference (Real-Time) | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $3.07 |
ml.g6e.4xlarge Inference (Real-Time) | Model inference on the ml.g6e.4xlarge instance type, real-time mode | $3.07 |
ml.g6e.8xlarge Inference (Real-Time) | Model inference on the ml.g6e.8xlarge instance type, real-time mode | $3.07 |
ml.g6e.16xlarge Inference (Real-Time) | Model inference on the ml.g6e.16xlarge instance type, real-time mode | $3.07 |
ml.g7.2xlarge Inference (Real-Time) | Model inference on the ml.g7.2xlarge instance type, real-time mode | $2.26 |
ml.g7.4xlarge Inference (Real-Time) | Model inference on the ml.g7.4xlarge instance type, real-time mode | $2.26 |
ml.g7.8xlarge Inference (Real-Time) | Model inference on the ml.g7.8xlarge instance type, real-time mode | $2.26 |
ml.g7e.2xlarge Inference (Real-Time) | Model inference on the ml.g7e.2xlarge instance type, real-time mode | $5.25 |
Vendor refund policy
Software fees for usage already consumed are non-refundable. If you were charged in error, contact support@gradium.ai within 30 days with your AWS account ID, endpoint name and dates; justified refunds are issued through AWS Marketplace. AWS infrastructure (instance) charges are not refundable by Gradium. To stop charges, delete your SageMaker endpoints: unsubscribing alone does not stop them.
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
Gradium real-time speech-to-text (model 55966eda@500, engine worker-xn 0.1.75). Batch size configurable per endpoint with the BATCH_SIZE environment variable (default 32).
Additional details
Inputs
- Summary
Real-time speech-to-text over SageMaker bidirectional streaming (InvokeEndpointWithBidirectionalStream). Send UTF-8 JSON messages, one per payload part:
- {"type": "setup", "model_name": "default", "input_format": "pcm"}, sent once. input_format is "pcm" (16-bit mono little-endian at 24 kHz), "wav" or "opus". An optional "json_config": {"language": "en"} sets the language.
- {"type": "audio", "audio": ""}, repeated as audio arrives. 80 ms chunks (1920 samples at 24 kHz) are recommended.
- {"type": "end_of_stream"} when the audio is finished.
- Limitations for input type
- Audio: mono, 24 kHz for "pcm" (other rates should be resampled). One stream lasts at most 30 minutes (SageMaker limit); reconnect for longer audio. Each instance serves BATCH_SIZE concurrent streams (default 32).
- Input MIME type
- application/json, application/octet-stream
{"type": "setup", "model_name": "default", "input_format": "pcm"}
{"type": "audio", "audio": "AAAAAAAA..."}
{"type": "end_of_stream"}
Not applicable: real-time streaming only.
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.
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.
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.
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.