> This page is for Platform.

> Fetch clean Markdown by appending `.md` to any page URL under https://signalwire.com/docs or requesting it with the HTTP header `Accept: text/markdown`. The root index at https://signalwire.com/docs/llms.txt lists the available documentation indexes.

## Six new text-to-speech engines

You can now use the [Groq](/docs/platform/voice/tts/groq-tts),
[Mistral](/docs/platform/voice/tts/mistral),
[Grok](/docs/platform/voice/tts/grok),
[Smallest.ai](/docs/platform/voice/tts/smallest),
[Fish Audio](/docs/platform/voice/tts/fish), and
[Speechify](/docs/platform/voice/tts/speechify)
TTS engines on the SignalWire platform.

## `playai-turbo` is now `groq-tts`

Groq retired PlayAI in December 2025.
The engine is renamed `groq-tts` and repointed at Canopy Labs' Orpheus, defaulting to `canopylabs/orpheus-v1-english`.

Arabic voices are available by selecting the `canopylabs/orpheus-arabic-saudi` model, or its shorthand `arabic`.
See [Groq](/docs/platform/voice/tts/groq-tts) for the voice list.

## Rime's `arcana` model is deprecated, falls back to `coda`

Rime retired its `arcana` model.
Applications that invoke it will fall back to `coda`, which shares voice names.

Additionally, the `coda` model now uses the same sampling parameters as other Rime models:
`repetition_penalty`, `temperature`, `top_p`, and `max_tokens`.

See [Rime](/docs/platform/voice/tts/rime).