signalwire · niravcodes · Dec 31, 2025 · Dec 4, 2025 · Dec 4, 2025 · Dec 5, 2025
@@ -61,13 +61,13 @@ self.add_language("English", "en-US", "elevenlabs.josh:eleven_turbo_v2_5")
 
 | Provider | Engine Code | Example Voice | Reference |
 |----------|-------------|---------------|-----------|
-| Amazon Polly | `amazon` | `amazon.Joanna-Neural` | [Voice IDs](https://developer.signalwire.com/voice/tts/amazon-polly#voice-ids) |
-| Cartesia | `cartesia` | `cartesia.a167e0f3-df7e-4d52-a9c3-f949145efdab` | [Voice IDs](https://developer.signalwire.com/voice/tts/cartesia#voice-ids) |
-| Deepgram | `deepgram` | `deepgram.aura-asteria-en` | [Voice IDs](https://developer.signalwire.com/voice/tts/deepgram#voice-ids) |
-| ElevenLabs | `elevenlabs` | `elevenlabs.thomas` | [Voice IDs](https://developer.signalwire.com/voice/tts/elevenlabs#voice-ids) |
-| Google Cloud | `gcloud` | `gcloud.en-US-Casual-K` | [Voice IDs](https://developer.signalwire.com/voice/tts/gcloud#voice-ids) |
-| Microsoft Azure | `azure` | `azure.en-US-AvaNeural` | [Voice IDs](https://developer.signalwire.com/voice/tts/azure#voice-ids) |
-| OpenAI | `openai` | `openai.alloy` | [Voice IDs](https://developer.signalwire.com/voice/tts/openai#voice-ids) |
+| Amazon Polly | `amazon` | `amazon.Joanna-Neural` | [Voice IDs](https://developer.signalwire.com/voice/tts/amazon-polly#usage) |
+| Cartesia | `cartesia` | `cartesia.a167e0f3-df7e-4d52-a9c3-f949145efdab` | [Voice IDs](https://developer.signalwire.com/voice/tts/cartesia#usage) |
+| Deepgram | `deepgram` | `deepgram.aura-asteria-en` | [Voice IDs](https://developer.signalwire.com/voice/tts/deepgram#usage) |
+| ElevenLabs | `elevenlabs` | `elevenlabs.thomas` | [Voice IDs](https://developer.signalwire.com/voice/tts/elevenlabs#usage) |
+| Google Cloud | `gcloud` | `gcloud.en-US-Casual-K` | [Voice IDs](https://developer.signalwire.com/voice/tts/gcloud#usage) |
+| Microsoft Azure | `azure` | `azure.en-US-AvaNeural` | [Voice IDs](https://developer.signalwire.com/voice/tts/azure#usage) |
+| OpenAI | `openai` | `openai.alloy` | [Voice IDs](https://developer.signalwire.com/voice/tts/openai#usage) |
 | Rime | `rime` | `rime.luna:arcana` | [Voice IDs](https://developer.signalwire.com/voice/tts/rime#voices) |
 
 ### Filler Phrases

@@ -4,26 +4,118 @@ description: Learn how to use Azure TTS voices on the SignalWire platform.
 slug: /voice/tts/azure
 ---
 
-import AzureVoices from './_azure-voices.mdx';
-
 # Microsoft Azure
 
 Microsoft's Azure platform offers an impressive array of high-quality, multilingual voices in its Neural model.
 
-## Languages
+## Voices {#voices}
+
+<CardGroup cols="2">
+  <Card title="Voices" href="https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=tts">
+    Browse the complete list of Azure Neural voices in Microsoft's official documentation.
+  </Card>
+  <Card title="Voice gallery" href="https://speech.microsoft.com/portal/voicegallery">
+    Listen to audio samples and preview voices in Azure's interactive voice gallery.
+  </Card>
+</CardGroup>
+
+## Usage {#usage}
+
+Azure voice IDs conform to the following format:
+
+```
+azure.<voice>
+```
+
+Where `<voice>` is the full Azure voice code (e.g., `en-US-AvaNeural`).
+
+**Examples:**
+```
+azure.en-US-AvaNeural
+azure.en-GB-SoniaNeural
+azure.de-DE-KatjaNeural
+azure.es-ES-ElviraNeural
+```
+
+**Note:** Azure voice IDs already include language information, so no additional language parameter is needed.
+
+## Languages {#languages}
 
 Azure Neural voices are interchangeably compatible with all supported languages.
 Rather than setting language with the language `code`,
 simply provide input text in the desired language.
 
-Consult the Azure 
+Consult the Azure
 [supported languages resource](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/language-support?tabs=tts)
 for an up-to-date list of supported languages.
 
-## Voice IDs
+## SSML support {#ssml}
+
+Azure voices support [Speech Synthesis Markup Language (SSML)](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup) for advanced control over:
+
+- Prosody (pitch, rate, volume)
+- Emphasis and breaks
+- Phonetic pronunciation
+- Multi-language content
+
+Consult Azure's [SSML documentation](https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup) for detailed usage instructions.
+
+---
 
-<div style={{"display":"inline-block","max-height":"70vh","overflow-y":"auto"}}>
+## Examples {#examples}
 
-<AzureVoices />
+Learn how to use Azure voices on the SignalWire platform.
 
-</div>
+<Tabs>
+<TabItem value="swml" label="SWML">
+Use the
+[**`languages`**](/swml/methods/ai/languages#use-voice-strings)
+SWML method to set one or more voices for an [AI agent](/swml/methods/ai).
+```yaml
+version: 1.0.0
+sections:
+  main:
+  - ai:
+      prompt:
+        text: Have an open-ended conversation about flowers.
+      languages:
+        - name: English
+          code: en-US
+          voice: azure.en-US-AvaNeural
+```
+Alternatively, use the [**`say_voice`** parameter](/swml/methods/play#parameters)
+of the [**`play`**](/swml/methods/play)
+SWML method to select a voice for basic TTS.
+```yaml
+version: 1.0.0
+sections:
+  main:
+  - set:
+      say_voice: "azure.en-US-AvaNeural"
+  - play: "say:Greetings. This is the Ava voice from Microsoft Azure's Neural text-to-speech model."
+```
+</TabItem>
+<TabItem value="relay" label="RELAY Realtime SDK">
+```javascript
+// This example uses the Node.js SDK for SignalWire's RELAY Realtime API.
+const playback = await call.playTTS({
+    text: "Greetings. This is the Ava voice from Microsoft Azure's Neural text-to-speech model.",
+    voice: "azure.en-US-AvaNeural",
+});
+await playback.ended();
+```
+</TabItem>
+<TabItem value="cfb" label="Call Flow Builder">
+Azure voices are not yet supported in Call Flow Builder.
+</TabItem>
+<TabItem value="cxml" label="cXML">
+```xml
+<?xml version="1.0" encoding="UTF-8"?>
+<Response>
+<Say voice="azure.en-US-AvaNeural">
+    Greetings. This is the Ava voice from Microsoft Azure's Neural text-to-speech model.
+</Say>
+</Response>
+```
+</TabItem>
+</Tabs>
@@ -9,14 +9,34 @@ import CodeBlock from '@theme/CodeBlock';
 # Cartesia
 
 Cartesia offers a wide selection of fully multilingual voices with very low latency.
+[Create a Cartesia account](https://play.cartesia.ai) to browse and test voices in the Cartesia Playground.
 
-Consult [Cartesia's Text-to-Speech documentation](https://docs.cartesia.ai/build-with-cartesia/models/tts)
-for more information and audio samples for available voices.
-[Create a Cartesia Account](https://play.cartesia.ai) to browse and test voices in the Cartesia Playground.
+## Models {#models}
 
-## Voice IDs
+Cartesia provides multiple generations of its Sonic TTS model:
 
-Copy the voice ID from the below table:
+| Model | Description |
+|-------|-------------|
+| `sonic-3` | **Default.** Latest model with enhanced naturalness |
+| `sonic-2` | Second-generation model with improved quality |
+| `sonic-turbo` | Optimized for ultra-low latency |
+| `sonic` | The first version of Sonic, optimized for accuracy and low latency. |
+
+
+All Cartesia voices can be used with any model.
+
+<CardGroup cols="2">
+  <Card title="Sonic 3" href="https://docs.cartesia.ai/build-with-cartesia/tts-models/latest">
+    Learn about Cartesia's latest Sonic 3 model.
+  </Card>
+  <Card title="Previous models" href="https://docs.cartesia.ai/build-with-cartesia/tts-models/older-models">
+    Documentation for older Sonic model versions.
+  </Card>
+</CardGroup>
+
+## Voices {#voices}
+
+Copy the voice ID from the table below:
 
 <div style={{"display":"inline-block","max-height":"70vh","overflow-y":"auto"}}>
 
@@ -153,14 +173,49 @@ Copy the voice ID from the below table:
 | British Customer Support Lady    | <CodeBlock>a01c369f-6d2d-4185-bc20-b32c225eab70</CodeBlock> |
 | Chinese Woman Narrator           | <CodeBlock>d4d4b115-57a0-48ea-9a1a-9898966c2966</CodeBlock> |
 
-</div><br /><br />
+</div>
+
+<br/>
+<br/>
+
+For more information, refer to Cartesia's guide to
+[Choosing a Voice](https://docs.cartesia.ai/build-with-cartesia/capability-guides/choosing-a-voice).
+
+## Usage {#usage}
+
+Cartesia voice IDs conform to the following format:
+
+```
+cartesia.<voice_id>:<model>
+```
+
+**Parameters:**
+- `voice_id` (required): The UUID voice identifier from the [Voices](#voices) table
+- `model` (optional): One of the Sonic models listed above (default: `sonic-3`)
+
+**Examples:**
+```
+cartesia.a167e0f3-df7e-4d52-a9c3-f949145efdab
+cartesia.694f9389-aac1-45b6-b726-9d9369183238:sonic-3
+cartesia.829ccd10-f8b3-43cd-b8a0-4aeaa81f3b30:sonic-turbo
+```
+
+## Languages {#languages}
+
+Cartesia voices are fully multilingual when used with `sonic-multilingual`, `sonic-2`, `sonic-3`, or `sonic-3` models. 
+The multilingual models automatically adapt to the input text language.
+
+Supported languages include: English, Spanish, French, German, Italian, Portuguese, Dutch, Polish, Russian, Chinese, Japanese, Korean, Hindi, Turkish, Swedish, and many more.
 
-Prepend `cartesia.` and the string is ready for use.
-For example: `cartesia.a167e0f3-df7e-4d52-a9c3-f949145efdab`
+For the complete list, refer to Cartesia's
+[Sonic 3 language support](https://docs.cartesia.ai/build-with-cartesia/tts-models/latest#language-support)
+and
+[Sonic 2 language support](https://docs.cartesia.ai/build-with-cartesia/tts-models/older-models#sonic-2-language-support)
+references.
 
 ---
 
-## Examples
+## Examples {#examples}
 
 See how to use Cartesia voices on the SignalWire platform.
 
@@ -204,7 +259,7 @@ await playback.ended();
 ```
 </TabItem>
 <TabItem value="cfb" label="Call Flow Builder">
-OpenAI voices are not yet supported in Call Flow Builder.
+Cartesia voices are not yet supported in Call Flow Builder.
 </TabItem>
 <TabItem value="cxml" label="CXML">
 ```xml

@@ -6,25 +6,67 @@ slug: /voice/tts/deepgram
 
 # Deepgram
 
-Deepgram offers a range of **English-speaking** voices for its text-to-speech API, each designed to produce
-natural-sounding speech output in an array of different accents and speaking styles.
+Deepgram's Aura model offers a wide range of voices for its text-to-speech API, 
+each designed to produce natural-sounding speech output in an array of different accents and speaking styles.
 
-Deepgram's voices are promised to have human-like tones, rhythm, and emotion, lower than 250 ms
-latency, and are optimized for high-throughput applications.
+Deepgram voices have human-like tones, rhythm, and emotion, 
+lower than 250 ms latency, 
+and are optimized for high-throughput applications.
 
-Consult Deepgram's [TTS models guide](https://developers.deepgram.com/docs/tts-models) 
+Consult Deepgram's [TTS models guide](https://developers.deepgram.com/docs/tts-models)
 for more information and samples for supported voices.
 
-## Voice IDs
+## Models {#models}
 
-Copy the voice ID from the **Values** column of Deepgram's
-[Voice Selection](https://developers.deepgram.com/docs/tts-models) reference.
-Prepend `deepgram.` and the string is ready for use.
-For example: `deepgram.aura-athena-en`
+Deepgram's Aura model provides ultra-low latency text-to-speech optimized for conversational AI:
+
+| Model | Description |
+|-------|-------------|
+| `aura` | **Default** - Low-latency conversational TTS with human-like tones |
+
+## Voices {#voices}
+
+Deepgram Aura voices are designed for natural-sounding English speech. Each voice follows the pattern `aura-<name>-en`.
+
+Popular voices include:
+- `aura-asteria-en` - Clear, professional female voice
+- `aura-luna-en` - Warm, conversational female voice
+- `aura-stella-en` - Energetic, friendly female voice
+- `aura-athena-en` - Authoritative female voice
+- `aura-hera-en` - Mature, confident female voice
+- `aura-orion-en` - Deep, authoritative male voice
+- `aura-arcas-en` - Professional male voice
+- `aura-perseus-en` - Friendly male voice
+- `aura-angus-en` - Casual male voice
+- `aura-orpheus-en` - Smooth, articulate male voice
+- `aura-helios-en` - Energetic male voice
+- `aura-zeus-en` - Powerful, commanding male voice
+
+For a complete list, consult Deepgram's [Voice Selection guide](https://developers.deepgram.com/docs/tts-models).
+
+## Usage {#usage}
+
+Deepgram voice IDs conform to the following format:
+
+```
+deepgram.<voice>
+```
+
+Where `<voice>` is the voice identifier from Deepgram's [Voice Selection](https://developers.deepgram.com/docs/tts-models) reference.
+
+Copy the voice ID from the **Values** column of Deepgram's Voice Selection reference, prepend `deepgram.`, and the string is ready for use.
+
+**Examples:**
+```
+deepgram.aura-asteria-en
+deepgram.aura-orion-en
+deepgram.aura-luna-en
+deepgram.aura-zeus-en
+```
 
 ---
 
-## Examples
+## Examples {#examples}
 
 Learn how to use Deepgram voices on the SignalWire platform.
 
@@ -80,4 +122,4 @@ Deepgram voices are not yet supported in Call Flow Builder.
 </Response>
 ```
 </TabItem>
-</Tabs>
+</Tabs>