Live virtual-microphone audio processing, not a documented public streaming inference API.
Batch processing
Not collected
No model-specific contract verified. Unknown does not mean unsupported.
Fine-tuning
Not collected
No model-specific contract verified. Unknown does not mean unsupported.
Reasoning
Not collected
No model-specific contract verified. Unknown does not mean unsupported.
Context caching
Not collected
No model-specific contract verified. Unknown does not mean unsupported.
Base model
Not collected
No model-specific contract verified. Unknown does not mean unsupported.
Model terms
Generic terms equate Real-Time Pro license to the Attribution license, while product pages promote professional call-center use. Exact commercial terms and plan-specific overrides require confirmation; do not infer unrestricted output rights.Source for Model terms (opens in a new tab)
Creation privacy
Standard Real-Time Pro pricing says voice audio stays on-device without provider storage/access. Discounted and Free subscriptions consent to anonymized voice data for model improvement; cloud processing is extra. Generic terms also permit diagnostics/source retention. Do not extend local Standard promises to all plans, cloud processing or every service.Source for Creation privacy (opens in a new tab)
Windows/macOS virtual microphone; local CPU processing or separately purchased Altered cloud processing. Cloud pricing lists US, EU and India server locations; exact routing, choice and data residency guarantees unverified.Source for Deployment options (opens in a new tab)
Hardware requirements
How-it-works page: minimum six CPU cores, 8 GB RAM; Intel efficiency/low-power cores excluded. Recommends 8+ cores and16 GB. Windows10 build1903+, Windows11, or macOS11+ on Apple Silicon. Page labels requirements for Euphonia; other model performance must be confirmed.Source for Hardware requirements (opens in a new tab)
Model selection
Euphonia is a provider model-family name in the Real-Time Pro app. App build freeze/rollback controls do not establish immutable neural checkpoints.Source for Model selection (opens in a new tab)
Input limits
Provider says source speech must already be intelligible. It is not a substitute for speech therapy or medical treatment; clinical efficacy and medical-device approval are not established by this page.Source for Input limits (opens in a new tab)
Voice controls
Dewhispering, irregular-voicing restoration, timing corrections and articulation adjustments are described. English-accent changes may occur; exact numeric controls and all supported languages are unverified.Source for Voice controls (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.
No callable public model ID or immutable checkpoint selector verified; UI names and voice-profile IDs are not API contracts.
Access
Licensed Windows/macOS virtual-microphone application. Use local CPU inference with a plan that includes the selected family. Download, biometric enrollment and performance were not tested.
Regions
Processing residency depends on deployment; no universal model-specific region guarantee verified.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 17 Oct 2026
Category
Usage
Rate
Unit
Real-Time Pro subscription
Euphonia Standard: monthly billing1
$12.00
subscription month
Real-Time Pro subscription
Euphonia Standard: annual billing2
$10.00
month equivalent, annual billing
Real-Time Pro subscription
Euphonia discounted: monthly billing3
$8.00
subscription month
Real-Time Pro subscription
Euphonia discounted: annual billing4
$6.00
month equivalent, annual billing
Rate conditions
Monthly billing. Excludes tax. Standard local processing: provider says voice data never leaves device. Unlimited processing. Voice Skins and Isolate are included alongside the named primary model in paid plans. Shared subscription across included models, not additive model fees. Cloud processing is a separate quota purchase.
Annual prepayment; displayed monthly equivalent. Excludes tax. Standard local processing: provider says voice data never leaves device. Unlimited processing. Voice Skins and Isolate are included alongside the named primary model in paid plans. Shared subscription across included models, not additive model fees. Cloud processing is a separate quota purchase.
Monthly billing. Excludes tax. Discounted subscription requires consent to anonymized voice data for model improvement. Unlimited processing. Voice Skins and Isolate are included alongside the named primary model in paid plans. Shared subscription across included models, not additive model fees. Cloud processing is a separate quota purchase.
Annual prepayment; displayed monthly equivalent. Excludes tax. Discounted subscription requires consent to anonymized voice data for model improvement. Unlimited processing. Voice Skins and Isolate are included alongside the named primary model in paid plans. Shared subscription across included models, not additive model fees. Cloud processing is a separate quota purchase.
Standard Real-Time Pro pricing says voice audio stays on-device without provider storage/access. Discounted and Free subscriptions consent to anonymized voice data for model improvement; cloud processing is extra. Generic terms also permit diagnostics/source retention. Do not extend local Standard promises to all plans, cloud processing or every service.
No callable public model ID or immutable checkpoint selector verified; UI names and voice-profile IDs are not API contracts.
Access
Select cloud compute in the licensed desktop application; buy a per-user daily-hour allowance. No public standalone model API or per-request token price established.
Regions
Pricing lists nearby servers in US, EU or India. Region-selection controls, routing and legal residency guarantees are not verified.
Published price
USD2 per purchased daily-quota hour per user per month, additional to model subscription. Example:4 hours/day for3 people costs USD24/month, not USD2 per actual processed audio hour.Source for Published price (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 17 Oct 2026
Category
Usage
Rate
Unit
Cloud processing add-on
Purchased daily-hour entitlement1
$2.00
daily-quota hour per user per month
Rate conditions
Separate from model subscription. Calculator multiplies2 × daily quota hours × team members. Quotas allocated independently per member; not USD2 per actual inference/audio hour. No token/question estimate.
Standard Real-Time Pro pricing says voice audio stays on-device without provider storage/access. Discounted and Free subscriptions consent to anonymized voice data for model improvement; cloud processing is extra. Generic terms also permit diagnostics/source retention. Do not extend local Standard promises to all plans, cloud processing or every service.
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.
Altered Real-Time Pro
Not verified
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
How it works
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Minimum reusable input
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Lifetime & refresh
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
How to enable it
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Usage fields
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Billing rules
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Limits & data boundaries
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 17 Oct 2026
Altered Real-Time Pro cloud
Not verified
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
How it works
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Minimum reusable input
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Lifetime & refresh
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
How to enable it
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Usage fields
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Billing rules
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
Limits & data boundaries
Not collected
No inference prompt-cache contract verified. Repeating a morph of the same input without additional quota, stored voice profiles and local processing are not token caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 17 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
Provider identifies its own voice-model families and retains proprietary rights in application/voices, restricts source access and model redistribution. Commercial desktop availability does not make these open-weight releases. Individual speakers and presets are not new base checkpoints.
