/ Tavus / Sparrow-2 Streaming conversational control model for turns, interruptions, backchannels and the full acoustic scene.
available Closed weights Turn detection
Context window Not collected Awaiting source review
Maximum output Not collected Awaiting source review
Input billing See rates Tavus CVI
Output billing See rates Published units and conditions below
Specifications Access & pricing Caching Evaluation Sources & lifecycle
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 Exact model-version information has not been established; unknown does not mean unsupported.
Maximum output Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Context caching Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Reasoning Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Tool calling Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Structured output Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Batch processing Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Fine-tuning Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Parameters Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Knowledge cutoff Not collected Exact model-version information has not been established; unknown does not mean unsupported.
Languages Not collected Exact model-version information has not been established; unknown does not mean unsupported.
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 sparrow-2
Access Set layers.conversational_flow.turn_detection_model=sparrow-2 when creating or updating a PAL.
Regions Privacy policy describes US processing and possible transfers to service providers in other countries. Exact model-serving location is not established. sessionLimits Table: Free 5 minutes, Starter 10, Builder 15, Growth/Business 60; Enterprise custom.Source for sessionLimits (opens in a new tab) The Growth hero says no duration limit, conflicting with the table. Confirm contractual limits.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026 Category Usage Rate Unit CVI bundle overage Builder full conversation pipeline1 $0.35 minute of CVI session CVI bundle overage Growth full conversation pipeline1 $0.31 minute of CVI session CVI bundle overage Business full conversation pipeline1 $0.26 minute of CVI session
Rate conditions Subscription and included allowance apply. Shared price for the complete pipeline; do not add component rates together. Each conversation has a 30-second minimum, rounded to the nearest 6 seconds. A created session can be billed even if no participant joins. Audio-only has the same current price. No text-token conversion. Pricing source (opens in a new tab) Data & enterprise terms Default privacy terms permit service improvement and AI research/training. Biometric retention is limited by the stated purpose or one year after last interaction, whichever comes first. Enterprise zero-retention arrangements are separate; no universal zero-retention promise is inferred.
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 INPUT Process & retain The system processes eligible input and retains reusable state.
02 / LATER REQUEST Check available state Reuse depends on matching input, session state and the cache policy.
03 / CACHE HIT Reuse & generate Reusing state can reduce repeated work. Any charges follow the billing rules below.
Tavus CVI sparrow-2Not verified Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
How it works Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
Minimum reusable input Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
Lifetime & refresh Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
How to enable it Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
Usage fields Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
Billing rules Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
Limits & data boundaries Not collected Internal streaming state, saved faces and conversation memories do not establish billable prompt caching, cache lifetime or discounts.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
TurnBench end-of-turn recall Tavus · provider-reported 92.4percent TurnBench result reported by Tavus in its release article. Independent benchmark owner records have not yet been cross-checked.
Evaluation source (opens in a new tab)
TurnBench interruption recall Tavus · provider-reported 97.4percent TurnBench result reported by Tavus in its release article. Independent benchmark owner records have not yet been cross-checked.
Evaluation source (opens in a new tab) 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 Named model developed by Tavus in its proprietary hosted/research stack. Reviewed primary documentation provides no downloadable weights for this model; service terms restrict source derivation and independent avatar use. Open SDKs and third-party models in the surrounding pipeline are separate.
Classification evidence (opens in a new tab) Lifecycle dates Sources reviewed Model notes Thirteen named native current, historical or restricted research models reviewed. Griffin-Lite is a restricted preview, not a general API release. Earlier codec revisions, forthcoming Griffin variants, hosted LLM adaptations and unpublished models remain under review.
Official Tavus provider artwork is used as the logo fallback; it is not a model-specific mark.
No exact general text context window, output-token allowance or prompt-cache tariff is established for this model.
The flow guide retains old sparrow-1 default headings alongside a September 8, 2026 default-switch notice. The current visible pricing table lists Sparrow-2. Explicit selection avoids relying on stale defaults.
Check against your workload Try representative inputs, measure task success and total cost, then check the exact endpoint’s data policy.
Read our methodology
Also from Tavus Phoenix-1 Phoenix-2 Phoenix-3 Phoenix-4 Phoenix-4.5 Raven-0 Raven-1 Sparrow-0 Sparrow-1 Hummingbird-0 Griffin-Lite Tavec v1.7 