Skip to content

Commit a695c6f

Browse files
hey-augusthey-august
authored
Update name and code in ai.languages params table (#485)
1 parent 9aa9e21 commit a695c6f

File tree

3 files changed

+16
-14
lines changed

3 files changed

+16
-14
lines changed

‎website/docs/main/home/calling/voice/tts/index.mdx‎

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,7 @@
11
---
22
slug: /voice/getting-started/voice-and-languages
33
author: Devon White, August Lindgren-Ruby
4+
title: Voices and Languages
45
x-custom:
56
tags:
67
- favorite
@@ -86,4 +87,4 @@ For detailed instructions for each provider, consult the voice ID references lin
8687

8788
## **Pricing**
8889

89-
See the [Voice API Pricing](https://signalwire.com/pricing/voice) page for up-to-date pricing information.
90+
See the [Voice API Pricing](https://signalwire.com/pricing/voice) page for up-to-date pricing information.

‎website/docs/main/home/calling/voice/tts/rime.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,7 @@
11
---
22
title: Rime TTS voices on the SignalWire Platform
33
slug: /voice/tts/rime
4-
sidebar_label: Rime 🔮
4+
sidebar_label: Rime
55
sidebar_position: 0
66
description: Learn how to use Rime's Arcana and Mist v2 TTS models with SignalWire AI Voice applications.
77
image: /docs/home/calling/voice/tts/preview.webp

‎website/docs/main/swml/methods/ai/ai_languages.mdx‎

Lines changed: 13 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -12,6 +12,7 @@ tags: ['swml']
1212
[tts-providers]: /voice/getting-started/voice-and-languages#providers
1313
[voices-and-languages]: /voice/getting-started/voice-and-languages
1414
[swaig-functions]: /swml/methods/ai/swaig/functions
15+
[deepgram-codes]: https://developers.deepgram.com/docs/models-languages-overview#nova-3
1516

1617
# ai.languages
1718

@@ -25,18 +26,18 @@ Use `ai.languages` to configure the spoken language of your AI Agent, as well as
2526

2627
## **Parameters for the `languages` object** {#languages-parameters}
2728

28-
| Name | Type | Default | Description |
29-
| :---------------------------------------------------------------------------------------------- | :------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
30-
| `name`<span className="required-arg">Required</span> | `string` | `English` | Name of the language ("French", "English", etc). |
31-
| `code`<span className="required-arg">Required</span> | `string` | `en-US` | The language code for the chosen voice, specified by the selected [TTS provider][tts-providers]. For example, `fr-FR`. |
32-
| [`voice`](#use-voice-strings)<span className="required-arg">Required</span> | `string` | [Standard-tier][voices-and-languages] voice picked by SignalWire | String format: `<engine id>.<voice id>`.<br/>Select engine from `gcloud`, `polly`, `elevenlabs`, or `deepgram`. Select voice from [TTS provider reference][tts-providers].<br/>For example, `"gcloud.fr-FR-Neural2-B"`. |
33-
| `emotion`<span className="optional-arg">Optional</span> | `string` | None | Enables emotion for the set TTS engine. This allows the AI to express emotions when speaking. A global emotion or specific emotions for certain topics can be set within the prompt of the AI.<br />*Valid values:** `auto`<br />**IMPORTANT:** Only works with `Cartesia` TTS engine. |
34-
| `function_fillers`<span className="optional-arg">Optional</span> | `string[]` | None | An array of strings to be used as fillers in the conversation when the agent is calling a [`SWAIG function`][swaig-functions]. The filler is played asynchronously during the function call. |
35-
| `model`<span className="optional-arg">Optional</span> | `string` | None | The model to use for the specified TTS engine (e.g. `arcana`). Check the [TTS provider reference][tts-providers] for the available models. |
36-
| `speech_fillers`<span className="optional-arg">Optional</span> | `string[]` | None | An array of strings to be used as fillers in the conversation. This helps the AI break silence between responses. |
37-
| `speed`<span className="optional-arg">Optional</span> | `string` | None | The speed to use for the specified TTS engine. This allows the AI to speak at a different speed at different points in the conversation. The speed behavior can be defined in the prompt of the AI.<br />*Valid values:** `auto`<br />**IMPORTANT:** Only works with [`Cartesia`](/voice/tts/cartesia) TTS engine. |
38-
| <span className="deprecated-arg">`fillers`</span><span className="optional-arg">Optional</span> | <span className="deprecated-arg">`string[]`</span> | <span className="deprecated-arg">None</span> | <span className="deprecated-arg">An array of strings to be used as fillers in the conversation and when the agent is calling a [`SWAIG function`][swaig-functions].</span><span className="deprecated-desc">**Deprecated**: Use `speech_fillers` and `function_fillers` instead.</span> |
39-
| <span className="deprecated-arg">`engine`</span><span className="optional-arg">Optional</span> | <span className="deprecated-arg">`string`</span> | <span className="deprecated-arg">`gcloud`</span> | <span className="deprecated-arg">The engine to use for the language. For example, `"elevenlabs"`.</span><span className="deprecated-desc">**Deprecated.** Set the engine with the [`voice`](#use-voice-strings) parameter.</span> |
29+
| Name | Type | Default | Description |
30+
| :---------------------------------------------------------------------------------------------- | :------------------------------------------------- | :--------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
31+
| `name`<span className="required-arg">Required</span> | `string` | `English` | Name of the language ("French", "English", etc). This value is used in the system prompt to instruct the LLM what language is being spoken. |
32+
| `code`<span className="required-arg">Required</span> | `string` | `en-US` | Set the language code for <Tooltips tip="Automatic Speech Recognition">ASR</Tooltips> (<Tooltips tip="Speech-to-text">STT</Tooltips>) purposes. By default, SignalWire uses Deepgram's Nova-3 STT engine, so this value should match a code from Deepgram's [Nova-3 language codes table][deepgram-codes].<br/><hr/>If a different STT model was selected using the [`openai_asr_engine` parameter](/swml/methods/ai/params), you must select a code supported by that engine. |
33+
| [`voice`](#use-voice-strings)<span className="required-arg">Required</span> | `string` | [Standard-tier][voices-and-languages] voice picked by SignalWire | String format: `<engine id>.<voice id>`.<br/>Select engine from `gcloud`, `polly`, `elevenlabs`, or `deepgram`. Select voice from [TTS provider reference][tts-providers].<br/>For example, `"gcloud.fr-FR-Neural2-B"`. |
34+
| `emotion`<span className="optional-arg">Optional</span> | `string` | None | Enables emotion for the set TTS engine. This allows the AI to express emotions when speaking. A global emotion or specific emotions for certain topics can be set within the prompt of the AI.<br />*Valid values:** `auto`<br />**IMPORTANT:** Only works with `Cartesia` TTS engine. |
35+
| `function_fillers`<span className="optional-arg">Optional</span> | `string[]` | None | An array of strings to be used as fillers in the conversation when the agent is calling a [`SWAIG function`][swaig-functions]. The filler is played asynchronously during the function call. |
36+
| `model`<span className="optional-arg">Optional</span> | `string` | None | The model to use for the specified TTS engine (e.g. `arcana`). Check the [TTS provider reference][tts-providers] for the available models. |
37+
| `speech_fillers`<span className="optional-arg">Optional</span> | `string[]` | None | An array of strings to be used as fillers in the conversation. This helps the AI break silence between responses.<hr/>Note that `speech_fillers` are used between every 'turn' taken by the LLM, including at the beginning of the call. For more targed fillers, consider using `function_fillers`. |
38+
| `speed`<span className="optional-arg">Optional</span> | `string` | None | The speed to use for the specified TTS engine. This allows the AI to speak at a different speed at different points in the conversation. The speed behavior can be defined in the prompt of the AI.<br />*Valid values:** `auto`<br />**IMPORTANT:** Only works with [`Cartesia`](/voice/tts/cartesia) TTS engine. |
39+
| <span className="deprecated-arg">`fillers`</span><span className="optional-arg">Optional</span> | <span className="deprecated-arg">`string[]`</span> | <span className="deprecated-arg">None</span> | <span className="deprecated-arg">An array of strings to be used as fillers in the conversation and when the agent is calling a [`SWAIG function`][swaig-functions].</span><span className="deprecated-desc">**Deprecated**: Use `speech_fillers` and `function_fillers` instead.</span> |
40+
| <span className="deprecated-arg">`engine`</span><span className="optional-arg">Optional</span> | <span className="deprecated-arg">`string`</span> | <span className="deprecated-arg">`gcloud`</span> | <span className="deprecated-arg">The engine to use for the language. For example, `"elevenlabs"`.</span><span className="deprecated-desc">**Deprecated.** Set the engine with the [`voice`](#use-voice-strings) parameter.</span> |
4041

4142
### Use `voice` strings
4243

0 commit comments

Comments
 (0)