Skip to content
Model infoModelsSnapshot: 15 Oct 2026

LOVO / Genny / LOVO speech synthesis

LOVO Pro Voices

Earlier proprietary Pro voice collection with contextual expressive speech, documented separately from Pro V2. Individual underlying checkpoints remain unpublished.

historicalClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 16 Oct 2026
8 of 23 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input billingNot collectedGenny web editor (historical)
Output billingNot collectedNo inferred price

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 model-specific specification verified; unknown is not unsupported.

Maximum input tokens
Not collected

No model-specific specification verified; unknown is not unsupported.

Maximum output
Not collected

No model-specific specification verified; unknown is not unsupported.

Parameters
Not collected

No model-specific specification verified; unknown is not unsupported.

Release date
Not collected

No model-specific specification verified; unknown is not unsupported.

Knowledge cutoff
Not collected

No model-specific specification verified; unknown is not unsupported.

Tool calling
Not collected

No model-specific specification verified; unknown is not unsupported.

Structured output
Not collected

No model-specific specification verified; unknown is not unsupported.

Streaming
Not collected

No model-specific specification verified; unknown is not unsupported.

Batch processing
Not collected

No model-specific specification verified; unknown is not unsupported.

Fine-tuning
Not collected

No model-specific specification verified; unknown is not unsupported.

Reasoning
Not collected

No model-specific specification verified; unknown is not unsupported.

Context caching
Not collected

No model-specific specification verified; unknown is not unsupported.

Base model
Not collected

No model-specific specification verified; unknown is not unsupported.

Endpoint availability
Historical documentation record. Public LOVO site and Genny app fetches returned HTTP 402 on October 16, 2026; the API schema remains reachable. Working signup, subscriptions and synthesis were not established. No formal retirement date is inferred from these observations.Source for Endpoint availability (opens in a new tab)
Published price
Not collected

No numeric rate verified from a working current first-party pricing page. The archived /pricing request resolves to homepage content. Third-party prices and old plan promotions are not treated as current tariffs.

Model terms
Archived terms reserve provider technology rights and restrict non-open-source reverse engineering. Subscription rights govern permitted use; ordinary commercial use does not include reselling or white-label access, which needs separate authorization. Uploaded content remains user-owned but grants broad service-operation/development rights; deletion has backup and re-sharing exceptions.Source for Model terms (opens in a new tab)
Creation privacy
September 2024 policy permits voice-data use to improve services provided to the user and related vendor processing. Account deletion has exceptions and cross-border processing is disclosed. Exact API retention, training opt-out and processing region are unverified. Policy scope differs between its opening and Linked Content sections; no blanket no-training or zero-retention claim.Source for Creation privacy (opens in a new tab)
Language coverage
Historical selection guide recommends Pro voices for English content. It does not publish an exhaustive per-model language list.Source for Language coverage (opens in a new tab)
Voice controls
Provider recommends longer multi-sentence blocks. It documents possible repeated phrases and prematurely cut-off endings; regenerated takes can differ. Same-text regeneration was described as not consuming additional generation credits in the editor.Source for Voice controls (opens in a new tab)

This historical editor behavior is not an API tariff, deterministic reuse or prompt-cache promise.

Documentation discrepancy
Historical emphasis tutorial reserves word-emphasis editing for Rapid voices and says Pro, Global and Custom voices do not support that control. Do not infer that Pro lacks all expressive delivery or transfer this restriction to later Pro V2.Source for Documentation discrepancy (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.

Genny web editor (historical)

Provider source (opens in a new tab)
API model ID
Not collected

Speaker/profile selector is not an immutable base-model ID. No family-specific API mapping established.

Access
Historical Genny Pro voice collection in the web editor. Current app access unverified; no immutable model selector or mapped API voice inventory.
Regions
Processing location unverified; company address is not inference residency.
Audio sample rates
44,100 HzSource for Audio sample rates (opens in a new tab)

Historical Genny downloaded-audio tutorial; external Audacity resampling is not a native alternative output rate. No specific codec inferred.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Historical September 2024 service terms apply by product/subscription scope; numeric current tariffs and current access are unverified. September 2024 policy permits voice-data use to improve services provided to the user and related vendor processing. Account deletion has exceptions and cross-border processing is disclosed. Exact API retention, training opt-out and processing region are unverified. Policy scope differs between its opening and Linked Content sections; no blanket no-training or zero-retention claim.

Read the service policy (opens in a new tab)

Caching

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.

Genny web editor (historical)

Not verified

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

How it works
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

Minimum reusable input
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

Lifetime & refresh
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

How to enable it
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

Usage fields
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

Billing rules
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state caching.

Limits & data boundaries
Not collected

No verified inference-cache contract. Free same-text regeneration and expiring audio links do not establish input-state 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

Provider identifies its Pro voice technology and Pro V2 launch separately from third-party multilingual voices; archived service terms reserve proprietary technology rights. These are closed model-family records, not published immutable weights or a claim that every named voice is a distinct model.

Classification evidence (opens in a new tab)

Sources reviewed