Sherpa TTS Node

SherpaTTS node is responsible for converting text into natural-sounding speech using advanced text-to-speech algorithms.

---

Configuration

text (Optional)

Type: String

Initial text to synthesize.

---

Values

Inherits values from its parent, SingleBusAudioSourceNode.

---

Actions

Inherits actions from its parent, SingleBusAudioSourceNode.

loadModel

Loads a Sherpa model from the provided paths.

Name	Type	Description
modelPath	String	Path to the sherpa model file.
tokensPath	String	Path to the sherpa tokens.
dataPath	String	Path to the sherpa data folder.

synthesize

Starts rendering of text as audio.

Parameters

Name	Type	Description
text	String	The text to synthesize.

---

Events

Inherits events from its parent, SingleBusAudioSourceNode.

---

Example

This example generates speech audio and renders it in real-time on the device's speaker.

JSON

{
    "type": "Realtime",
    "config": {
        "graph": {
            "config": {
                "sampleRate": 16000,
                "bufferSize": 512
            },
            "nodes": [
                {
                    "id": "ttsNode",
                    "type": "Sherpa.SherpaTTSNode"
                },
                {
                    "id": "monoToMultiChannelNode",
                    "type": "MonoToMultiChannel"
                }
            ],
            "connections": [
                {
                    "sourceNode": "ttsNode",
                    "destinationNode": "monoToMultiChannelNode"
                },
                {
                    "sourceNode": "monoToMultiChannelNode",
                    "destinationNode": "outputNode"
                }
            ]
        }
    }
}

To generate speech with the TTS node, call the synthesize action and provide the desired text as a parameter.

C++

auto result = Switchboard::callAction("ttsNode", "synthesize", { { "text", text } });