Rime | SignalWire

Rime offers uniquely realistic voices with a focus on natural expressiveness.

Models

Model	Description
`coda`	Rime’s flagship model, with top-rated, ultra-realistic voices
`mistv2`	Default - Updated version of mist
`arcana` Deprecated	Retired by Rime. Requests for `arcana` are served by `coda` — use `coda` instead.
`mist` Deprecated	Fast, precise model for business applications

Coda

Coda is Rime’s flagship model, pairing a sophisticated LLM backbone with a dedicated speech inference engine for top-rated, ultra-realistic voices.

Mist v2

Mist is Rime’s fastest model, built for high-volume, business-critical applications.

Voices

Press play to audition any Rime voice, then copy config to grab the value for SWML or your SDK.

Mist v2 is the default Rime model on the SignalWire platform. To use this model, simply set the voice ID.

To use Coda voices, set model to coda with the languages SWML method:

1 languages:
2 - name: English
3   code: en-US
4   voice: rime.luna
5   model: coda

Languages

As of July 20th, 2026, SignalWire supports the following languages with Rime:

Language	Code	Supported models
English	`eng`	All models
Spanish	`spa`	All models
French	`fra`	All models
German	`ger`	All models
Portuguese	`por`	`coda`
Hindi	`hin`	`coda`
Arabic	`ara`	`coda`
Japanese	`jpn`	`coda`

Portuguese, Hindi, Arabic, and Japanese voices are available with the coda model only. The default mistv2 model supports English, Spanish, French, and German. To use the other languages, set model to coda as shown above.

Refer to the Rime docs for the most up-to-date reference to supported languages.

Usage

Format: rime.<speaker>:<model>

Examples:

rime.luna:coda
rime.spore:coda
rime.speaker1:mistv2
rime.voice123:mist

For a full demonstration and sample script, see below.

Rime dashboard

Preview Rime voices on their dashboard

Rime docs

Refer to the Rime Docs for an up-to-date list of voice IDs.

Build with Rime on SignalWire

Create a Space and add credit

If you don’t have one yet, you’ll need to create a SignalWire Space. Be sure to add some credit to test with.

Add a new Resource

Navigate to the Resources tab in your SignalWire Dashboard and click + Add New to create a new Resource.

Create a SWML Script

From the Resources menu, select SWML Script. Name it something fun and recognizable. Ours is titled Rime Wizard.

Next, paste the following starter script into the text box, and hit Save:

1 version: 1.0.0
2 sections:
3   main:
4   - ai:
5       prompt:
6         text: | 
7           You're Luna, a voice from Rime's Coda model! 
8           Introduce yourself, and have a conversation about programmable unified communications on the SignalWire platform. 
9       languages:
10       - name: English
11         code: en-US
12         voice: rime.luna
13         model: coda

Buy and assign a phone number

Navigate to the Phone Numbers section of the Dashboard’s left sidebar menu.

Purchase a phone number and assign it to the desired SWML script.

A purchased phone number showing assignment to a specified Resource. — Assigning a phone number to the SWML Script

Give it a call!

Call the number you just assigned to chat with your new AI voice application on the phone.

Next steps with SWML

Now you’ve deployed your very first SignalWire voice AI application using Rime voices. Next, dive deeper into SWML to explore its capabilities!

Methods reference

Documentation for all SWML methods

AI in SWML

Build advanced AI applications using SignalWire Markup Language

Guides

SWML guides and demo applications