Managed voice-catalogue service documented with synchronous and asynchronous TTS endpoints. The catalogue mixes voice groups and third-party technology; current inference access is unverified.
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)
Public API request text range 1–500 characters; not a token window or editor limit.
Authentication
X-API-KEY header; keys were generated in Genny. Account-linked TTS credits are deducted. GET /api/v1/teams/status exposes subscription state and usage metadata, not public numeric prices.Source for Authentication (opens in a new tab)
API requires speaker and text; optional speakerStyle and speed 0.05–3, default 1. Only some speakers have styles. No request fields for pause, emphasis or pronunciation are defined in this public schema even though response metadata includes them.Source for Voice controls (opens in a new tab)
Integrated speech providers
Archived provider homepage FAQ explicitly attributes multilingual voices to ElevenLabs. Exact ElevenLabs version and all other voice-group backend mappings are unknown; do not attribute the entire catalogue to LOVO-native models.Source for Integrated speech providers (opens in a new tab)
Stock voice catalog
Historical editor groups: Pro, Rapid, Global, Multilingual and Emotional, with later Pro V2 launch documented separately. API GET /api/v1/speakers is paginated and authenticated; returns voice IDs, locales, styles and sample URLs. Example IDs/locales are not a complete current catalogue.Source for Stock voice catalog (opens in a new tab)
Public OpenAPI separately defines API catalogue fields. Exact production speaker inventory was not fetched.
Language coverage
Historical platform marketing says 500+ voices across 100 languages. This is aggregate mixed-provider coverage, not a verified matrix for every model or API entitlement.Source for Language coverage (opens in a new tab)
Billing basis
Historical web generation allowance is measured by generated audio duration. The public API says it deducts account-linked TTS credits, without a public numeric currency tariff or universal conversion.Source for Billing basis (opens in a new tab)
API billing description is separately linked. Do not convert audio minutes into text-token or question prices.
Response format
Sync POST waits at most 90 seconds and can return an incomplete job with HTTP 201. Async POST returns a job ID; poll GET /api/v1/tts/{jobId}. Job status is in_progress/done, but each output is pending/succeeded/failed and may carry an error. Check output success and URLs, not just done or HTTP status. Fixed response JSON is not caller-defined structured generation.Source for Response format (opens in a new tab)
Output link expiry
Result audio URLs are valid for 24 hours. This describes download-link availability, not deletion of every stored input, voice model, output or backup.Source for Output link expiry (opens in a new tab)
Completion callbacks
Async callbackUrls prose permits at most four URLs, sent once via POST. A receiver must return 2xx within 10 seconds. Callback body follows job retrieval response. The schema omits maxItems despite the prose maximum; no retry guarantee.Source for Completion callbacks (opens in a new tab)
Documentation discrepancy
Tutorial includes pending at job level; schema only enumerates in_progress/done there and pending at output level. Job-type enum includes dubbing/localization/subtitles while its description says only TTS is supported. These enum values do not establish public APIs for those tasks. Speaker styles use an object allOf shape despite plural wording; verify actual response before assuming an array.Source for Documentation discrepancy (opens in a new tab)
Audio sample rates
Not collected
Web download tutorial says 44.1 kHz, but public API does not establish a codec/sample-rate contract. Do not infer API encoding from web exports.
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Speaker/profile selector is not an immutable base-model ID. No family-specific API mapping established.
Access
Documented POST https://api.genny.lovo.ai/api/v1/tts/sync with X-API-KEY and JSON text/speaker. Waits up to 90 seconds; incomplete job can require polling. Documentation remains public, but authenticated inference was not tested.
Regions
Processing location unverified; company address is not inference residency.
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.
Speaker/profile selector is not an immutable base-model ID. No family-specific API mapping established.
Access
Documented POST https://api.genny.lovo.ai/api/v1/tts with X-API-KEY, JSON text/speaker and optional callbackUrls. Retrieve result via GET /api/v1/tts/{jobId}; check each output status. Current account access unverified.
Regions
Processing location unverified; company address is not inference residency.
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.
Speaker/profile selector is not an immutable base-model ID. No family-specific API mapping established.
Access
Historical Genny web catalogue including Pro, Rapid, Global, Multilingual and Emotional voices. Third-party multilingual backend attribution is documented; no claim that each group is a distinct private model.
Regions
Processing location unverified; company address is not inference residency.
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.
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 API
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
Genny API
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
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
Proprietary hosted speech service using catalogue speakers. Official FAQ attributes multilingual voices to ElevenLabs; unspecified native and hosted backends are not counted as separate Genny-owned checkpoints.
