Groq | SignalWire

Groq hosts Canopy Labs’ Orpheus text-to-speech models, offering fast, expressive voices in English and Arabic.

The groq-tts engine replaces the retired playai-turbo engine. If you were using playai-turbo voices, switch to groq-tts with one of the voices below.

Models

SignalWire supports the following Orpheus models on Groq. See Groq’s text-to-speech documentation for more detail.

Model	Description
`canopylabs/orpheus-v1-english`	Default. English voices
`canopylabs/orpheus-arabic-saudi`	Arabic (Saudi dialect) voices. The shorthand `arabic` also selects this model

The Arabic model requires accepting Canopy Labs’ model terms in the Groq console for the account making the requests. Requests fail until the terms are accepted.

Voices

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

Groq’s Orpheus deployment provides the following voices:

Voice	Description
`autumn`	Female. Used as the fallback when an unrecognized voice is requested
`diana`	Female
`hannah`	Female
`austin`	Male
`daniel`	Male
`troy`	Male

Preview the voices in Groq’s documentation:

Groq TTS docs

Reference for Orpheus models and voices on Groq.

Groq console

Try Orpheus voices in the Groq playground.

Expressive speech

Orpheus supports inline vocal direction tags in the text to be spoken, such as <giggle> and <sigh>, to add expressiveness. The speed setting is not supported.

Languages

Each model supports one language:

Language	Model
English	`canopylabs/orpheus-v1-english`
Arabic (Saudi)	`canopylabs/orpheus-arabic-saudi`

Usage

A voice identifier string has three parts: the groq-tts engine code, a voice ID, and an optional model.

Format: groq-tts.<voiceId>:<model>

voiceId (required): one of the voices above (for example, autumn).
model (optional): one of the models above. Defaults to canopylabs/orpheus-v1-english.

Examples:

groq-tts.autumn
groq-tts.troy:canopylabs/orpheus-v1-english
groq-tts.daniel:arabic

You can also set the model with the separate model parameter of the languages SWML method instead of appending :model to the voice string:

1 languages:
2 - name: English
3   code: en-US
4   voice: groq-tts.autumn
5   model: canopylabs/orpheus-v1-english

Build with Groq 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 Groq 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 Autumn, a voice from the Orpheus TTS engine hosted on Groq!
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: groq-tts.autumn

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 Groq-hosted Orpheus 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