Output billingSee ratesPublished units and conditions below
Specifications
Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.
Context / input limit
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Maximum input tokens
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Maximum output
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Parameters
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Release date
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Knowledge cutoff
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Tool calling
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Structured output
Not collected
No reviewed model-specific specification; unknown is not unsupported.
Streaming
Not collected
SageMaker real-time inference is a request/response deployment mode, not proof of chunked audio streaming. The vendor notebook reads the complete response.
Provider describes an LLM-based speech synthesis model; exact architecture and parameter count are undisclosed in the reviewed listing.Source for Architecture (opens in a new tab)
API parameters
Vendor input example is JSON with text; batch sample is JSON lines containing text. The notebook reads the response as audio and saves output.wav. Voice selectors, output-rate choices and production input limits are not specified.Source for API parameters (opens in a new tab)
An example output format does not establish the complete codec contract.
Published price
AWS Marketplace lists $100 per ml.g5.2xlarge host-hour for real-time inference and $100 per host-hour for batch inference. These are software charges; AWS infrastructure costs are additional. Character-based Typecast SaaS plans do not apply to this listing.Source for Published price (opens in a new tab)
Voice cloning
Vendor overview advertises a 10-second voice reference. Its supplied input example exposes only text, so clone parameters and actual endpoint support are unresolved.Source for Voice cloning (opens in a new tab)
Documentation discrepancy
The pinned deployment notebook references a different Marketplace product page and a sample us-east-1 ARN, contains template placeholders and does not implement its advertised batch section. Treat it as illustrative; obtain the actual model package ARN from the selected current listing and region. The marketing history says 2025 for SSFM 2.0, while artifact identifiers/older materials are not a reliable release date.Source for Documentation discrepancy (opens in a new tab)
Model terms
Vendor EULA grants restricted personal/internal-business software use, reserves model IP and prohibits redistribution and reverse engineering subject to applicable law. Technical support information may be used for product improvement. SaaS API content terms must not automatically be applied to this separately licensed deployment.Source for Model terms (opens in a new tab)
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Marketplace version label; deployment uses a region-specific model package ARN, not this string as a public Typecast API model parameter.
Access
Licensed model package for SageMaker real-time endpoints on ml.g5.2xlarge. Requires a subscription, IAM permissions and AWS infrastructure. No deployment performed.
Regions
Region chosen during Marketplace configuration. Pinned sample us-east-1 ARN and CI template badges do not establish complete currently supported regions.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 16 Oct 2026
Category
Usage
Rate
Unit
AWS real-time software
ml.g5.2xlarge software usage1
$100.00
host-hour
Rate conditions
Published software price for the selected deployment mode. Underlying SageMaker infrastructure and storage are additional. Not a per-audio-hour, token, character or question price.
Separate model-software EULA permits support-related technical information collection. Data handling also depends on the customer AWS configuration and AWS terms; no zero-retention or model-training guarantee established by this EULA.
Marketplace version label; deployment uses a region-specific model package ARN, not this string as a public Typecast API model parameter.
Access
Licensed model package for SageMaker batch transform on ml.g5.2xlarge. Requires a subscription, IAM permissions and AWS infrastructure. No deployment performed.
Regions
Region chosen during Marketplace configuration. Pinned sample us-east-1 ARN and CI template badges do not establish complete currently supported regions.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 16 Oct 2026
Category
Usage
Rate
Unit
AWS batch software
ml.g5.2xlarge software usage1
$100.00
host-hour
Rate conditions
Published software price for the selected deployment mode. Underlying SageMaker infrastructure and storage are additional. Not a per-audio-hour, token, character or question price.
Separate model-software EULA permits support-related technical information collection. Data handling also depends on the customer AWS configuration and AWS terms; no zero-retention or model-training guarantee established by this EULA.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
AWS Marketplace / Amazon SageMaker
ssfm-v20
Not verified
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
How it works
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Minimum reusable input
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Lifetime & refresh
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
How to enable it
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Usage fields
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Billing rules
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Limits & data boundaries
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
AWS Marketplace / Amazon SageMaker
ssfm-v20
Not verified
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
How it works
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Minimum reusable input
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Lifetime & refresh
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
How to enable it
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Usage fields
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Billing rules
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
Limits & data boundaries
Not collected
No native inference cache contract established. Custom voice profiles, downloaded audio and retained generation history are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Neosapience explicitly describes its history of proprietary speech model development. Current API selectors, licensed AWS software and historical generation labels are distinguished. Public TA2.0 avatar weights are a different model and are excluded.
