Original expressive speech generation release. Its original cloud weights are no longer selected by the Arcana alias, which later advanced and now routes to Coda.
Pre-trained LLM backbone with additional text/audio pretraining; autoregressively decodes flattened codec representations from coarsest to finestSource for Architecture (opens in a new tab)
Use of an open-source backbone does not make the resulting proprietary speech checkpoint open-weight.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Rime documents character-count-only collection by default and no customer-content model training without opt-in. Optional request retention is disabled by default and can be enabled for support/quality investigation; enabling it does not authorize training. Voice-clone recordings have separate customer-specific training permission. MSA/BAA terms may vary.
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.
Rime API
arcana
Not verified
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
How it works
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
Minimum reusable input
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
Lifetime & refresh
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
How to enable it
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
Usage fields
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
Billing rules
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
Limits & data boundaries
Not collected
No model-specific prompt-cache contract or discounted cached-character rate established. TensorRT engine caches, persistent sockets and speaker profiles are not prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
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
Rime reserves ownership of its AI voice models and grants a limited service license. Current Coda/Mist deployments explicitly use private, closed-source licensed engine images; Together describes Arcana as proprietary. The separately released Rimecaster speaker-embedding model is CC-BY-4.0 and is excluded.
