Audio sample ratesHistorical SDK documents 8/16/24 kHz, default 24 kHz except µ-law at 8 kHz. Default format mp3; exhaustive original Aurora format coverage unverified.See specification notes below
LanguagesNot collectedAwaiting source review
Input billingNot collectedLMNT API (retired)
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 does not mean unsupported.
Maximum input tokens
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Maximum output
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Parameters
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Release date
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Knowledge cutoff
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Tool calling
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Structured output
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Streaming
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Batch processing
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Fine-tuning
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Reasoning
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Context caching
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Base model
Not collected
No model-specific specification verified. Unknown does not mean unsupported.
Endpoint availability
Original Aurora generation was replaced in May 2025: the aurora ID began routing to Blizzard. The later provider shutdown is separate; a surviving alias would not prove original Aurora weights remain accessible.Source for Endpoint availability (opens in a new tab)
Creation privacy
Archived June 2023 policy allows user-content use for machine-learning training and human review. Personal information is generally retained until edited/deleted or while the person remains a user; no fixed inference-retention period or zero-retention promise established. US and other international transfers are described. Post-shutdown deletion and handling are unverified.Source for Creation privacy (opens in a new tab)
Model terms
Archived site terms describe personal, noncommercial site access; historical paid API plans advertise commercial licenses. These have different scopes, so neither a universal commercial prohibition nor unrestricted commercial rights is inferred. Separate service restrictions protect model weights. Current contractual status after shutdown is unknown.Source for Model terms (opens in a new tab)
aurora was the default selector in the historical v1.2.0 SDK. Starting May 2025 it routes to Blizzard; no immutable original checkpoint selector verified.Source for Model selection (opens in a new tab)
Voice controls
Historical SDK: speed 0.25–2.0 (default 1.0), optional target length up to 300 seconds, random seed and conversational flag. Target length is a request control, not a verified hard output-duration ceiling. Speed and length are sent only when the selector is aurora.Source for Voice controls (opens in a new tab)
Audio sample rates
Historical SDK documents 8/16/24 kHz, default 24 kHz except µ-law at 8 kHz. Default format mp3; exhaustive original Aurora format coverage unverified.Source for Audio sample rates (opens in a new tab)
Languages
Not collected
Historical SDK defaults language to en and accepts language codes, but a complete original Aurora language list was not recovered. Do not inherit Blizzard 1.4’s 31-language list.
Published price
Not collected
No version-dated original Aurora tariff verified. August 2026 plans postdate the May 2025 routing change.
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Original historical selector; later redirected to Blizzard, not an immutable weight pin.
Access
LMNT has shut down. Historical contracts below do not establish a callable service. Exact shutdown date and any continuing third-party deployment are unverified. Historical POST https://api.lmnt.com/v1/ai/speech with model=aurora, text and voice. JSON base64 audio, optional word durations/seed. Since May 2025 this selector routes to Blizzard.
Regions
Historical inference residency unverified. Company location is not processing-region evidence.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Archived June 2023 policy allows user-content use for machine-learning training and human review. Personal information is generally retained until edited/deleted or while the person remains a user; no fixed inference-retention period or zero-retention promise established. US and other international transfers are described. Post-shutdown deletion and handling are unverified. Archived site terms describe personal, noncommercial site access; historical paid API plans advertise commercial licenses. These have different scopes, so neither a universal commercial prohibition nor unrestricted commercial rights is inferred. Separate service restrictions protect model weights. Current contractual status after shutdown is unknown.
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.
LMNT API (retired)
aurora
Not verified
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
How it works
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
Minimum reusable input
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
Lifetime & refresh
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
How to enable it
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
Usage fields
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
Billing rules
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input caching.
Limits & data boundaries
Not collected
No inference-cache contract verified. Persistent speech sessions, stored voice prompts, saved clips, SDK cached properties and random seeds are not discounted input 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
Official model overview and release notes identify LMNT speech models; service policy explicitly restricts discovery of its models and model weights. Open client code and unrelated public DiffWave/WaveGrad research do not establish published Aurora or Blizzard weights.
