Sold by: NVIDIA
Deployed on AWS
Natural and expressive voices in multiple languages. For voice agents and brand ambassadors.
Overview
The Magpie TTS Multilingual model converts text into audio (speech).
Magpie TTS is a generative model, designed to be used as the first part of a neural text-to-speech system in conjunction with an audio codec model. This model uses the International Phonetic Alphabet (IPA) for inference and training, and it can output a female or a male voice for English-US and European-Spanish. In addition, it uses character-based encoding for French.
Audio Codec is a neural codec model for speech applications. It is the second part of a two-stage speech synthesis pipeline.
This model is ready for commercial use.
Highlights
- Robust T5-TTS Architecture: T5-TTS is an encoder-decoder transformer designed for stable text-to-speech synthesis. It significantly improves robustness by enforcing monotonic alignment, ensuring the model reads text in the correct order without skipping or repeating words. The system accepts text tokens and reference audio codes as input, then autoregressively predicts the specific acoustic tokens required to generate the target speech.
- High-Efficiency 21Hz Audio Codec: The system employs a specialized neural audio compression model that quantizes signals into discrete tokens at an aggressively low rate of 21 frames per second (Hz). It uses multi-stage encoding to analyze longer audio windows, capturing essential acoustic features before downsampling. This allows the model to compress input audio into a compact sequence of codes while preserving the core voice characteristics despite the heavy temporal compression.
- High-Fidelity Neural Reconstruction: To recover audio from the compressed 21Hz tokens, the model utilizes advanced neural upsampling techniques during the decoding phase. This reconstructs high-fidelity sound at the original sampling rate, effectively bridging the gap between the low-rate tokens and clear audio output. This architecture optimizes the balance between storage efficiency and audio quality, making it ideal for scalable speech synthesis applications.
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.g5.48xlarge Inference (Batch) Recommended | Model inference on the ml.g5.48xlarge instance type, batch mode | $8.00 |
ml.g6e.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g6e.xlarge instance type, real-time mode | $1.00 |
ml.g6e.2xlarge Inference (Real-Time) | Model inference on the ml.g6e.2xlarge instance type, real-time mode | $1.00 |
ml.g6e.4xlarge Inference (Real-Time) | Model inference on the ml.g6e.4xlarge instance type, real-time mode | $1.00 |
ml.g6e.8xlarge Inference (Real-Time) | Model inference on the ml.g6e.8xlarge instance type, real-time mode | $1.00 |
ml.g6e.16xlarge Inference (Real-Time) | Model inference on the ml.g6e.16xlarge instance type, real-time mode | $1.00 |
ml.g6e.12xlarge Inference (Real-Time) | Model inference on the ml.g6e.12xlarge instance type, real-time mode | $4.00 |
ml.g6e.24xlarge Inference (Real-Time) | Model inference on the ml.g6e.24xlarge instance type, real-time mode | $4.00 |
ml.g6e.48xlarge Inference (Real-Time) | Model inference on the ml.g6e.48xlarge instance type, real-time mode | $8.00 |
ml.p4d.24xlarge Inference (Real-Time) | Model inference on the ml.p4d.24xlarge instance type, real-time mode | $8.00 |
Vendor refund policy
No Refund.
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
- Summary
Magpie TTS Multilingual accepts JSON requests via the /invocations API. The request contains the input text and optional synthesis controls (voice, language, sample rate, encoding). The container can route requests to NIM over HTTP or gRPC internally; you can force gRPC using CustomAttributes="/invocations/grpc".
- Input MIME type
- application/json
{
"text": "Hello, this is a Magpie TTS test.",
"language_code": "en-US",
"voice_name": "Magpie-Multilingual.EN-US.Aria",
"sample_rate_hz": 44100,
"encoding": "LINEAR_PCM"
}
{
"text": "Hello, this is a Magpie TTS test.",
"language_code": "en-US",
"voice_name": "Magpie-Multilingual.EN-US.Aria",
"sample_rate_hz": 44100,
"encoding": "LINEAR_PCM"
}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
text | Text to synthesize.
| String | Yes |
language_code | Language code (e.g., en-US, es-US, fr-FR, , de-DE, zh-CN, vi-VN, it-IT). Default en-US.
| String | No |
voice_name | Voice name (e.g., Magpie-Multilingual.EN-US.Aria).
| String | No |
sample_rate_hz | Output sample rate (e.g., 44100).
| Integer | No |
encoding | Output encoding (e.g., LINEAR_PCM, OGGOPUS). Default LINEAR_PCM.
| String | No |
custom_dictionary | Pronunciation dictionary string in NIM format: "Word phonemes,Word2 phonemes2". Presence auto-triggers gRPC path.
| String | No |
zero_shot_data | Enables zero-shot voice cloning (gRPC path). Contains base64 audio_prompt plus optional quality and transcript.
| Object | No |
Resources
Support
Vendor support
Free support via NVIDIA NIM Developer Forum:
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
NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines development and deployment of production-grade AI applications, including generative AI.
The NVIDIA GPU-Optimized AMI is an environment for running the GPU-accelerated deep learning and HPC containers from the NVIDIA NGC catalog. The deep learning containers from NGC catalog require this AMI for GPU acceleration on AWS P5d, P4d, P3, G4dn, G5 GPU instances.
NVIDIA Nemotron-4 15B NIM is a 15-billion-parameter large multilingual language model trained on 8T tokens of multilingual, and coding tasks
NVIDIA Isaac Sim™ Development Workstation (Linux) is preconfigured with the software tools for accelerating and scaling your robotic simulation workloads from synthetic data generation to software-in-loop testing of your robotics stack.
The NVIDIA Omniverse™ Development Workstation (Linux) provides a pre-configured environment containing the software and drivers required to accelerate Omniverse development.
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.