ComfyUI Node: Edge TTS 🔊

Edge TTS 🔊:

EdgeTTS is a node designed to generate speech from text using Microsoft's Edge online text-to-speech service. This node is integrated into ComfyUI, providing a seamless way to convert written text into spoken words. It leverages the capabilities of Edge TTS to produce high-quality audio outputs, making it an invaluable tool for AI artists who wish to incorporate voice elements into their projects. The node simplifies the process of text-to-speech conversion by handling the complexities of audio generation, allowing you to focus on the creative aspects of your work. By using EdgeTTS, you can easily transform text into audio with customizable voice, speed, and pitch settings, ensuring that the output aligns with your artistic vision.

Edge TTS 🔊 Input Parameters:

text

The text parameter is the core input for the EdgeTTS node, representing the written content you wish to convert into speech. It is crucial to ensure that the text is not empty, as the node requires valid input to function correctly. The text is processed and transformed into audio, with the quality and clarity of the output depending on the content provided. There are no specific minimum or maximum values for this parameter, but it should be a meaningful string of text.

voice

The voice parameter allows you to select the specific voice that will be used to generate the speech. This parameter is essential for customizing the audio output to match your desired tone and style. While the context does not specify the available options, it is likely that a range of voices is supported by the Edge TTS service. If the selected voice fails to produce audio, the node will attempt to use a default voice as a fallback.

speed

The speed parameter controls the rate at which the text is spoken. It is expressed as a percentage, with a default value of 1.0, representing normal speed. Adjusting this parameter allows you to speed up or slow down the speech, providing flexibility in how the audio is presented. The speed is calculated as a percentage change from the default rate, with positive values increasing the speed and negative values decreasing it.

pitch

The pitch parameter adjusts the pitch of the generated speech, allowing you to modify the tone of the voice. It is expressed in Hertz (Hz) and can be set to positive or negative values to increase or decrease the pitch, respectively. This parameter is useful for fine-tuning the audio output to better fit the mood or character you are trying to convey.

Edge TTS 🔊 Output Parameters:

waveform

The waveform output parameter represents the audio data generated by the EdgeTTS node. It is a tensor containing the waveform of the spoken text, which can be used for further processing or playback. The waveform is normalized to ensure consistent audio levels, making it suitable for integration into various projects.

sample_rate

The sample_rate output parameter indicates the sample rate of the generated audio. It is a crucial aspect of the audio data, as it defines the number of samples per second in the waveform. A higher sample rate generally results in better audio quality, providing a more accurate representation of the original speech.

Edge TTS 🔊 Usage Tips:

• Ensure that the text parameter is not empty to avoid errors and ensure successful audio generation.
• Experiment with different voice, speed, and pitch settings to achieve the desired audio output that best fits your project.
• Use the waveform and sample_rate outputs to integrate the generated audio into your projects, ensuring compatibility with other audio processing tools.

Edge TTS 🔊 Common Errors and Solutions:

Input text cannot be empty

• Explanation: This error occurs when the text parameter is empty or contains only whitespace.
• Solution: Provide a valid string of text to the text parameter to ensure successful audio generation.

Failed with voice <voice>, trying default voice <default_voice>

• Explanation: This warning indicates that the selected voice failed to produce audio, and the node is attempting to use a default voice as a fallback.
• Solution: Verify that the selected voice is supported by the Edge TTS service, or consider using the default voice if the issue persists.

NoAudioReceived

• Explanation: This error occurs when no audio is received from the Edge TTS service, possibly due to network issues or unsupported voice settings.
• Solution: Check your network connection and ensure that the selected voice and other parameters are valid. Retry the operation or use a different voice if necessary.