> 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. # Voices and languages > Detailed list of all the TTS providers and voices SignalWire supports. [polly]: /docs/platform/voice/tts/amazon-polly [azure]: /docs/platform/voice/tts/azure [cartesia]: /docs/platform/voice/tts/cartesia [deepgram]: /docs/platform/voice/tts/deepgram [elevenlabs]: /docs/platform/voice/tts/elevenlabs [fish]: /docs/platform/voice/tts/fish [gcloud]: /docs/platform/voice/tts/gcloud [grok]: /docs/platform/voice/tts/grok [groq]: /docs/platform/voice/tts/groq-tts [inworld]: /docs/platform/voice/tts/inworld [minimax]: /docs/platform/voice/tts/minimax [mistral]: /docs/platform/voice/tts/mistral [openai]: /docs/platform/voice/tts/openai [rime]: /docs/platform/voice/tts/rime [smallest]: /docs/platform/voice/tts/smallest [speechify]: /docs/platform/voice/tts/speechify SignalWire integrates natively with leading third-party text-to-speech (TTS) providers. This guide describes supported engines, voices, and languages. Refer to each provider's documentation for up-to-date model details and service information. ## Browse and audition voices Browse each provider's complete voice list on its reference page, linked in the table below. ## Compare providers and models SignalWire's TTS providers offer a wide range of voice engines optimized for various applications. Select a provider, model, and voice according to the following considerations: **Language support:** At time of writing, engine language support is as follows. Consult each provider's reference documentation for the most up-to-date information. * [Rime][rime] voices support English, Spanish, French, German, Portuguese, Hindi, Arabic, and Japanese. * [Deepgram][deepgram] voices support English, Spanish, German, French, Dutch, Italian, and Japanese. * [Amazon Polly][polly], [Azure][azure], [Cartesia][cartesia], and [Google Cloud][gcloud] offer a wide range of supported languages. * [Inworld][inworld] voices support English plus Arabic, Chinese (Mandarin), Dutch, French, German, Hebrew, Hindi, Italian, Japanese, Korean, Polish, Portuguese, Russian, and Spanish. * [MiniMax][minimax] voices span more than 20 languages, including English, Spanish, Portuguese, French, German, Italian, Chinese, Japanese, Korean, and many more, with automatic language detection. * [Fish Audio][fish] voices cover roughly 83 languages on the `s2.1-pro` model, with automatic language detection. * [Mistral][mistral] voices support English, French, Spanish, Portuguese, Italian, Dutch, German, Hindi, and Arabic. * [Smallest.ai][smallest] voices support English, Spanish, Hindi, and nine other Indian languages. * [Speechify][speechify] voices are multilingual on the `simba-3.0` model. * [Groq][groq]-hosted Orpheus voices support English and Arabic (Saudi), one language per model. * All [ElevenLabs][elevenlabs], [OpenAI][openai], and [Grok][grok] voices are fully multilingual. **SSML support:** Google Cloud and Amazon Polly support SSML (Speech Synthesis Markup Language) as a string wrapped in `` tags. Consult [Google Cloud's SSML docs](https://cloud.google.com/text-to-speech/docs/ssml) for details. Refer to the Amazon Polly docs for more information on [using SSML](https://docs.aws.amazon.com/polly/latest/dg/ssml.html) and [supported SSML tags.](https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html) ## Use voice identifier strings Compose voice identifier strings using the following general format: ``` engine.voice:model ``` | Identifier | Description | | ----------------- | ------------------------------------------------------- | | `engine` required | The TTS provider (e.g., `elevenlabs`, `rime`, `openai`) | | `voice` required | The voice identifier (name or ID depending on engine) | | `model` optional | Model variant (not all engines support this) | > **Info** > > Since voice ID strings are case insensitive, the following strings are equivalent: > > ``` > gcloud.en-US-Neural2-A > gcloud.en-us-neural2-a > GCLOUD.EN-US-NEURAL2-A > ``` For detailed instructions for each provider, consult the voice ID references linked in the **Usage** column of the below table. | TTS provider | Sample voice ID string | Usage | | :----------- | :----------------------------------------------- | -------------------------------------------------------- | | Amazon Polly | `amazon.Joanna-Neural` | [Reference](/docs/platform/voice/tts/amazon-polly#usage) | | Azure | `azure.en-US-AvaNeural` | [Reference](/docs/platform/voice/tts/azure#usage) | | Cartesia | `cartesia.a167e0f3-df7e-4d52-a9c3-f949145efdab` | [Reference](/docs/platform/voice/tts/cartesia#usage) | | Deepgram | `deepgram.aura-asteria-en` | [Reference](/docs/platform/voice/tts/deepgram#usage) | | ElevenLabs | `elevenlabs.thomas` | [Reference](/docs/platform/voice/tts/elevenlabs#usage) | | Fish Audio | `fish.802e3bc2b27e49c2995d23ef70e6ac89:s2.1-pro` | [Reference](/docs/platform/voice/tts/fish#usage) | | Google Cloud | `gcloud.en-US-Casual-K` | [Reference](/docs/platform/voice/tts/gcloud#usage) | | Grok | `grok.eve` | [Reference](/docs/platform/voice/tts/grok#usage) | | Groq | `groq-tts.autumn` | [Reference](/docs/platform/voice/tts/groq-tts#usage) | | Inworld | `inworld.Lauren:inworld-tts-1.5-mini` | [Reference](/docs/platform/voice/tts/inworld#voices) | | MiniMax | `minimax.English_CalmWoman:speech-2.6-turbo` | [Reference](/docs/platform/voice/tts/minimax#voices) | | Mistral | `mistral.` | [Reference](/docs/platform/voice/tts/mistral#usage) | | OpenAI | `openai.alloy` | [Reference](/docs/platform/voice/tts/openai#usage) | | Rime | `rime.luna:coda` | [Reference](/docs/platform/voice/tts/rime#voices) | | Smallest.ai | `smallest.sophia:lightning_v3.1` | [Reference](/docs/platform/voice/tts/smallest#usage) | | Speechify | `speechify.alicia:simba-3.0` | [Reference](/docs/platform/voice/tts/speechify#usage) | ## Custom and cloned voices SignalWire's TTS integrations run on SignalWire's own accounts with each provider. When you set a voice string like `elevenlabs.` or `cartesia.:`, SignalWire resolves the voice ID against its own provider account — not yours. > **Warning** > > Only voices from SignalWire's catalog resolve on the platform. > A voice ID from your own provider account — including custom or cloned voices — is not visible > to SignalWire's account. It will not resolve, and TTS falls back to a default voice at call time. > This applies even though a cloned-voice ID looks identical in format to a catalog voice ID. ElevenLabs custom and cloned voices can be imported into SignalWire's catalog by request. [Contact Support](https://support.signalwire.com/portal) to request a voice import. Once the voice is imported, use it with the standard [voice string format](/docs/platform/voice/tts/elevenlabs#usage). \ ## **Pricing** See the [Voice API Pricing](https://signalwire.com/pricing/voice) page for up-to-date pricing information. > Detailed list of all the TTS providers and voices SignalWire supports. ## Docs - [Amazon Polly](https://signalwire.com/docs/platform/voice/tts/amazon-polly.md): Learn how to use Polly TTS voices on the SignalWire platform. - [Azure](https://signalwire.com/docs/platform/voice/tts/azure.md): Learn how to use Azure TTS voices on the SignalWire platform. - [Cartesia](https://signalwire.com/docs/platform/voice/tts/cartesia.md): Learn how to use Cartesia TTS voices on the SignalWire platform. - [Deepgram](https://signalwire.com/docs/platform/voice/tts/deepgram.md): Learn how to use Deepgram TTS voices on the SignalWire platform. - [ElevenLabs](https://signalwire.com/docs/platform/voice/tts/elevenlabs.md): Learn how to use ElevenLabs TTS voices on the SignalWire platform. - [Fish Audio](https://signalwire.com/docs/platform/voice/tts/fish.md): Learn how to use Fish Audio's marketplace and cloned TTS voices with SignalWire AI Voice applications. - [Google Cloud](https://signalwire.com/docs/platform/voice/tts/gcloud.md): Learn how to use Google Cloud TTS voices on the SignalWire platform. - [Grok](https://signalwire.com/docs/platform/voice/tts/grok.md): Learn how to use xAI's Grok TTS voices with SignalWire AI Voice applications. - [Groq](https://signalwire.com/docs/platform/voice/tts/groq-tts.md): Learn how to use Groq-hosted Orpheus TTS voices with SignalWire AI Voice applications. - [Inworld](https://signalwire.com/docs/platform/voice/tts/inworld.md): Learn how to use Inworld's expressive, multilingual TTS models with SignalWire AI Voice applications. - [MiniMax](https://signalwire.com/docs/platform/voice/tts/minimax.md): Learn how to use MiniMax's expressive, multilingual TTS voices with SignalWire AI Voice applications. - [Mistral](https://signalwire.com/docs/platform/voice/tts/mistral.md): Learn how to use Mistral's Voxtral TTS voices with SignalWire AI Voice applications. - [OpenAI](https://signalwire.com/docs/platform/voice/tts/openai.md): Learn how to use OpenAI TTS voices on the SignalWire platform. - [Rime](https://signalwire.com/docs/platform/voice/tts/rime.md): Learn how to use Rime's Coda and Mist v2 TTS models with SignalWire AI Voice applications. - [Smallest.ai](https://signalwire.com/docs/platform/voice/tts/smallest.md): Learn how to use Smallest.ai's Waves Lightning TTS voices with SignalWire AI Voice applications. - [Speechify](https://signalwire.com/docs/platform/voice/tts/speechify.md): Learn how to use Speechify's Simba TTS voices with SignalWire AI Voice applications.