Models are constantly being trained and finetuned based on user and customer feedback. Please check back often as we push changes frequently.
There are currently 3 models that Rime has in production, arcana
, mistv2
and mist
.
Arcana, released April 2025, is Rime’s most expressive and lifelike TTS model to date. It pushes the boundary of naturalness and emotional depth in synthesized speech.
modelId: arcana
through Rime’s API endpointsMistv2, released February 2025 has the following features:
Mist is Rime’s next generation TTS engine, released April 2023, capable of synthesizing conversational speech. Using the modelId
parameter for Rime’s TTS endpoints, specifying mistv2
or mist
, will allow you to synthesize speech using this newer family of models. As of February 2025, the default value for modelId
when unspecified is mist
.
Model v1 was released in April 2022 and has been deprecated.
Arcana also supports several additional controls due to its LLM backbone. We recommend leaving these on the default values.
temperature
: Controls the randomness of the generated speech.
repetition_penalty
: Discourages the model from repeating the same sounds.
top_p
: Determines the diversity of choices by limiting the selection to a subset of probable sounds.
See the Arcana API reference pages for more details.
Models are constantly being trained and finetuned based on user and customer feedback. Please check back often as we push changes frequently.
There are currently 3 models that Rime has in production, arcana
, mistv2
and mist
.
Arcana, released April 2025, is Rime’s most expressive and lifelike TTS model to date. It pushes the boundary of naturalness and emotional depth in synthesized speech.
modelId: arcana
through Rime’s API endpointsMistv2, released February 2025 has the following features:
Mist is Rime’s next generation TTS engine, released April 2023, capable of synthesizing conversational speech. Using the modelId
parameter for Rime’s TTS endpoints, specifying mistv2
or mist
, will allow you to synthesize speech using this newer family of models. As of February 2025, the default value for modelId
when unspecified is mist
.
Model v1 was released in April 2022 and has been deprecated.
Arcana also supports several additional controls due to its LLM backbone. We recommend leaving these on the default values.
temperature
: Controls the randomness of the generated speech.
repetition_penalty
: Discourages the model from repeating the same sounds.
top_p
: Determines the diversity of choices by limiting the selection to a subset of probable sounds.
See the Arcana API reference pages for more details.