Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Smallest AI / Lightning

Lightning V3.2

Instruction-controlled speech synthesis with a published WebSocket example and a separate voice catalog.

availableClosed weightsText-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
10 of 22 specification fields collected
Output formatsPCM16 monoSee specification notes below
Languages2 listedFull language list in specifications
Input billingNot collectedSmallest AI API
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
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
English, HindiSource for Languages (opens in a new tab)

Registry language metadata can lag the current model card; auto is routing metadata, not another language.

Context caching
Not collected
Native model options
lightning-v3.2Source for Native model options (opens in a new tab)

Registry identifier uses hyphens; unified TTS request selectors for v3.1/v3.2 use underscores.

Voice cloning
Not supportedSource for Voice cloning (opens in a new tab)

Voice cloning is not evidence of user access to base-model fine-tuning. Legacy flags do not imply current clone creation works.

Stock voice catalog
14 public stock voices mapped to lightning-v3.2 on 2026-10-13Source for Stock voice catalog (opens in a new tab)

Snapshot count, not a permanent service limit. Presets are not independent model checkpoints.

Output formats
PCM16 monoSource for Output formats (opens in a new tab)

Format used by the official example, not an exhaustive API format list.

Audio sample rates
44,100 Hz in the official exampleSource for Audio sample rates (opens in a new tab)
Voice controls
Emotion, pitch, volume and prosody instructions are advertised; the official example leaves these fields disabled because some inputs cause playback errorsSource 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.

API model ID
lightning_v3.2
Access
Official cookbook uses wss://api.smallest.ai/waves/v1/tts/live with a Bearer API key. The general HTTP schema currently lists only v3.1 pools.
Regions
Automatic routing to Mumbai, India or Oregon, USA; api.india.smallest.ai and api.us.smallest.ai pin a region. Language availability can differ by region.
API endpoint URL
wss://api.smallest.ai/waves/v1/tts/liveSource for API endpoint URL (opens in a new tab)

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

Data & enterprise terms

Content is retained unless an eligible Enterprise data policy is enabled. Options: no content storage, a 24-hour to 90-day window, or x-expire-content: true for seven-day expiry. On other plans the header is ignored. Billing/usage metadata remains; settings are not retroactive. TTS saved history is excluded from window expiry. Speech-to-speech and cloning are not expressly covered.

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.

Smallest AI API

lightning_v3.2
Not verified

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

How it works
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

Minimum reusable input
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

Lifetime & refresh
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

How to enable it
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

Usage fields
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

Billing rules
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

Limits & data boundaries
Not collected

No discounted prompt-cache contract verified for this model/access route. Audio continuity and model-weight storage are separate features.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

14 voices

Choose a voice within Lightning V3.2. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
Abbieabbieenglish
british
Provider voice label: female. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Sloanesloaneenglish
american
Provider voice label: female. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Wrenwrenenglish
american
Provider voice label: female. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Reedreedenglish
american
Provider voice label: male. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Marlowemarloweenglish
american
Provider voice label: female. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Knoxknoxenglish
american
Provider voice label: male. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Tatetateenglish
american
Provider voice label: female. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)
Kierankieranenglish
british
Provider voice label: male. Language tags describe the voice; they do not override endpoint language restrictions.Voice source (opens in a new tab)

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

Smallest retains rights in its AI models and prohibits model extraction. Its model cards name Smallest as developer; Electron, Hydra and Lightning v3.1 explicitly use proprietary licenses. Commercial self-hosting requires licensed artifacts and a license proxy, not an open-weight grant.

Classification evidence (opens in a new tab)

Sources reviewed