Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Tavus / Raven

Raven-1

Live audiovisual perception model that supplies contextual descriptions and action triggers to a conversation pipeline.

availableClosed weightsExpression analysis
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
6 of 17 specification fields collected
Measured expressionsNot collectedAwaiting source review
Face limitsNot collectedAwaiting source review
Input billingSee ratesTavus CVI
Output billingSee ratesPublished units and conditions below

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
SupportedSource for Tool calling (opens in a new tab)

Perception-triggered actions in the PAL system; separate from general-purpose LLM tool selection.

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.

Architecture
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.

Output modalities
TextSource for Output modalities (opens in a new tab)

Contextual observations for a downstream LLM; not a general chat or standalone speech generation model.

Provider-reported latency
Sub-100 ms audio perception; combined context described as at most 300 ms staleSource for Provider-reported latency (opens in a new tab)

Provider-reported system behavior, not a public latency guarantee.

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
raven-1
Access
Set layers.perception.perception_model=raven-1 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.
analysisLimits
Audio-analysis annotation: at most 32 tokens per utterance; analysis queries and tool definitions: at most 10,000 characters each.Source for analysisLimits (opens in a new tab)

These are field-specific bounds, not the model context or universal output-token limit.

perceptionInputs
Camera, shared screen and user audio. Visual awareness updates throughout the call; audio context accompanies utterances.Source for perceptionInputs (opens in a new tab)
emotionControls
emotion_recognition: full, limited or auto. Limited omits biometric emotion inference; auto follows the conversation policy.Source for emotionControls (opens in a new tab)

Emotion descriptions are model interpretations, not measurements of a person’s internal state.

analysisDelivery
Live visual/audio annotations inform the downstream LLM. perception_analysis_queries shape end-of-call summaries and do not change live behavior.Source for analysisDelivery (opens in a new tab)
Billing and deployment scope
CVI bundle includes Phoenix-4.5, Raven-1, Sparrow-2, LLM, TTS and WebRTC. These are shared bundle charges, not standalone or additive component prices.Source for Billing and deployment scope (opens in a new tab)
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.

Concurrent requests
Free/Starter 1; Builder 3; Growth 10; Business 15; Enterprise custom.Source for Concurrent requests (opens in a new tab)
Subscription eligibility
Starter $22/month with 60 minutes and no overage; Builder $59 with 175; Growth $397 with 1,300; Business $975 with 4,000; Enterprise custom.Source for Subscription eligibility (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
CVI bundle overageBuilder full conversation pipeline1$0.35minute of CVI session
CVI bundle overageGrowth full conversation pipeline1$0.31minute of CVI session
CVI bundle overageBusiness full conversation pipeline1$0.26minute of CVI session

Rate conditions

  1. 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 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.

Tavus CVI

raven-1
Not 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

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

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

Named release announced10 Feb 2026Source (opens in a new tab)

Sources reviewed