timeScaleFactor 0.4–2.5, clamped: values above 1 slow speech. Compatibility speedAlpha has the opposite direction. Mist v3 inlineSpeedAlpha works only over HTTP.Source for Generation controls (opens in a new tab)
Dedicated speed guide takes precedence over conflicting legacy/host parameter descriptions.
Managed enterprise clone: 30–60 minutes clean audio for a basic clone; 2–5 hours or more recommended. Mono WAV/FLAC, at least 44.1 kHz and 16-bit. Assigned speaker UUID only works on the model(s) used for training.Source for Voice cloning (opens in a new tab)
Associated model/engine/API builds in the changelog, not distinct foundation checkpoints or a promise that old images remain supported. Some entries include shared API-service tags.
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech synthesis
Starter speech synthesis1
$50.00
1M characters
Rate conditions
Converted from $0.05/1,000 characters. Character billing, not tokens or a fixed audio-minute rate. Starter concurrency 20; enterprise terms negotiated. Free allowance is inconsistent across the page (about 800 minutes vs 3,000), so no exact free quota is assumed.
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.
Parameters are fixed at connection creation. segment=bySentence/never/immediate controls when buffered text is synthesized; explicit flush is available. Inline per-word speed is not read by WebSocket endpoints.Source for Generation controls (opens in a new tab)
The per-word restriction is established in the speed guide, even though legacy parameter lists still show inlineSpeedAlpha.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech synthesis
Starter speech synthesis1
$50.00
1M characters
Rate conditions
Converted from $0.05/1,000 characters. Character billing, not tokens or a fixed audio-minute rate. Starter concurrency 20; enterprise terms negotiated. Free allowance is inconsistent across the page (about 800 minutes vs 3,000), so no exact free quota is assumed.
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.
Parameters are fixed at connection creation. segment=bySentence/never/immediate controls when buffered text is synthesized; explicit flush is available. Inline per-word speed is not read by WebSocket endpoints.Source for Generation controls (opens in a new tab)
The per-word restriction is established in the speed guide, even though legacy parameter lists still show inlineSpeedAlpha.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech synthesis
Starter speech synthesis1
$50.00
1M characters
Rate conditions
Converted from $0.05/1,000 characters. Character billing, not tokens or a fixed audio-minute rate. Starter concurrency 20; enterprise terms negotiated. Free allowance is inconsistent across the page (about 800 minutes vs 3,000), so no exact free quota is assumed.
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.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech synthesis
Starter speech synthesis1
$50.00
1M characters
Rate conditions
Converted from $0.05/1,000 characters. Character billing, not tokens or a fixed audio-minute rate. Starter concurrency 20; enterprise terms negotiated. Free allowance is inconsistent across the page (about 800 minutes vs 3,000), so no exact free quota is assumed.
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.
Parameters are fixed at connection creation. segment=bySentence/never/immediate controls when buffered text is synthesized; explicit flush is available. Inline per-word speed is not read by WebSocket endpoints.Source for Generation controls (opens in a new tab)
The per-word restriction is established in the speed guide, even though legacy parameter lists still show inlineSpeedAlpha.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech synthesis
Starter speech synthesis1
$50.00
1M characters
Rate conditions
Converted from $0.05/1,000 characters. Character billing, not tokens or a fixed audio-minute rate. Starter concurrency 20; enterprise terms negotiated. Free allowance is inconsistent across the page (about 800 minutes vs 3,000), so no exact free quota is assumed.
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.
Parameters are fixed at connection creation. segment=bySentence/never/immediate controls when buffered text is synthesized; explicit flush is available. Inline per-word speed is not read by WebSocket endpoints.Source for Generation controls (opens in a new tab)
The per-word restriction is established in the speed guide, even though legacy parameter lists still show inlineSpeedAlpha.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Speech synthesis
Starter speech synthesis1
$50.00
1M characters
Rate conditions
Converted from $0.05/1,000 characters. Character billing, not tokens or a fixed audio-minute rate. Starter concurrency 20; enterprise terms negotiated. Free allowance is inconsistent across the page (about 800 minutes vs 3,000), so no exact free quota is assumed.
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.
Single engine serves HTTP POST / or /invocations, gRPC and WebSocket. Protocol envelopes differ from cloud ws3; all share one capacity pool.Source for Request mode (opens in a new tab)
Specific on-prem release behavior, not a global native-cloud audio cap.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Runtime license checked locally; aggregate usage counts sent over HTTPS to Rime. Synthesis text and audio remain in the deployment. A metering outage does not stop synthesis; in-memory reports retry and older pending windows can be dropped.
Exact image from official deployment config, not a guarantee of the latest cloud checkpoint.
Access
Licensed private single-container deployment in the customer’s Baseten workspace. The repository currently pins an older image than the on-prem quickstart; confirm image/license compatibility.
Regions
Region selected in the customer’s Baseten workspace.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Rime license and metering credentials are supplied as secrets; callers authenticate to Baseten. Complete host retention and operational terms require the deployment contract.
LiveKit documents no inference-content retention by default, including underlying providers, with optional observability and voice storage handled separately.
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
coda
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.
Rime API
coda
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.
Rime API
coda
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.
Rime API
coda
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.
Rime API
coda
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.
Rime API
coda
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.
Licensed on-prem deployment
us-docker.pkg.dev/rime-labs/coda/v1/coda:20260923
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.
Baseten
us-docker.pkg.dev/rime-labs/coda/v1/coda:20260620
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.
LiveKit Inference
rime/coda
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.
Voice choices
287 voices
Choose a voice within Coda. These are API voice identifiers, not additional model releases. Source links document each voice.
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.
