Qwen3 TTS Simple Text to Speech ComfyUI workflow for Videcool

The Qwen3 TTS Simple Text to Speech workflow in Videcool provides a fast and practical way to generate speech from text prompts. Designed for simplicity, clarity, and creative control, this workflow is served by ComfyUI and uses the Qwen3 TTS model to synthesize spoken audio from text with a selectable built-in speaker voice.

What can this ComfyUI workflow do?

In short: Text-to-speech synthesis with selectable speaker voices.

This workflow takes text input and synthesizes new speech audio using the Qwen3 TTS model. It loads the model from Hugging Face, applies settings such as language, speaker, seed, instruction text, custom speaker name, and token limit, then produces an MP3 audio output. The attached workflow is optimized for simple local text-to-speech generation without requiring a reference audio sample or a separate voice cloning stage.

Example usage in Videcool

Figure 1 - Qwen3 TTS Simple Text to Speech ComfyUI workflow in Videcool

Download the ComfyUI workflow

Download ComfyUI Workflow file: qwen3_simple_text_to_speech-api.json

Image of the ComfyUI workflow

This figure provides a visual overview of the workflow layout inside ComfyUI. Each node is placed in logical order to establish a clean and efficient text-to-speech pipeline. The structure makes it easy to understand how the Qwen3 model loader, custom voice generation node, and MP3 audio output node interact. Users can modify the text, selected speaker, language, and token settings to create custom narration or integrate speech generation into larger audio or video production pipelines.

Figure 2 - Qwen3 TTS Simple Text to Speech workflow

Installation steps

Step 1: Install the ComfyUI custom nodes or extension package that provides the Qwen3Loader and Qwen3CustomVoice nodes required by this workflow.
Step 2: Ensure ComfyUI can access the model repository Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice, because the workflow is configured to load the model from Hugging Face with source="HuggingFace", precision="bf16", and attention="auto".
Step 3: If preferred, configure a local model path supported by the custom node package, because the workflow also includes a local_model_path field, which is empty in the attached JSON.
Step 4: Download the qwen3_simple_text_to_speech-api.json workflow file into your home directory.
Step 5: Restart ComfyUI so the custom node and model files are recognized.
Step 6: Open the ComfyUI graphical user interface (ComfyUI GUI).
Step 7: Load the qwen3_simple_text_to_speech-api.json workflow in the ComfyUI GUI.
Step 8: Enter the text you want to synthesize in the Qwen3-TTS Custom Voice node, then choose the desired language and built-in speaker voice. The attached workflow uses language="English" and speaker="Eric".
Step 9: Optionally adjust seed, instruct, custom_speaker_name, and max_new_tokens. The attached workflow uses seed 42, an empty instruction field, an empty custom speaker name, and max_new_tokens=2048.
Step 10: Run the workflow to synthesize speech and save the output as an MP3 file through the Save Audio (MP3) node. The default filename prefix is audio/ComfyUI and the MP3 quality is set to V0.
Step 11: Open Videcool in your browser, select the Text to Speech tool, and use the generated audio in your video, narration, or dubbing projects.

Installation video

The workflow requires only text input and a few simple parameter choices to begin generating speech. After loading the JSON file, users can enter the text to be spoken, choose a language, select a speaker voice from the dropdown, and optionally adjust seed or token settings. Once executed, the model generates speech audio and saves it as an MP3 file that can be reused across other Videcool tools.

Prerequisites

To run the workflow correctly, install the ComfyUI custom nodes that provide the Qwen3 TTS loader and custom voice generation nodes, then make sure the model repository or local model files are accessible to ComfyUI. These components ensure the workflow can process text, load the Qwen3 TTS model, generate speech with a selected speaker, and save the result as an MP3 file. Proper installation into your ComfyUI custom node and model environment is essential before running the workflow.

Model repository used by the workflow
https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Custom node classes required by the workflow
Qwen3Loader
Qwen3CustomVoice
SaveAudioMP3

How to use this workflow in Videcool

Videcool integrates seamlessly with ComfyUI, allowing users to generate speech directly without managing the underlying node graph. After importing the workflow file, simply enter your text, select the language and desired speaker voice, and click generate. The system handles the backend interaction with ComfyUI, making text-to-speech intuitive and accessible even for users who do not want to work directly with ComfyUI nodes.

ComfyUI nodes used

This workflow uses the following nodes. Each node performs a specific role, such as loading the Qwen3 TTS model, processing text input, selecting a speaker voice, synthesizing speech, and finally saving the output. Together they create a compact and reliable pipeline that can be easily extended or customized.

Qwen3-TTS Loader
Qwen3-TTS Custom Voice
Save Audio (MP3)

Base AI model

This workflow is built on the Qwen3 TTS model identified in the attached JSON as Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice. The workflow loads it from Hugging Face with BF16 precision and automatic attention settings, then generates speech through the Qwen3CustomVoice node using text, language, speaker choice, and optional instruction parameters.

Speech quality and parameters

Speech quality in this workflow depends on the entered text, selected language, chosen speaker voice, and generation settings. The attached workflow uses English language mode, the built-in speaker Eric, seed 42, an empty instruction field, no custom speaker name, and a maximum of 2048 new tokens, which provides a simple starting configuration for general text-to-speech tasks.

Conclusion

The Qwen3 TTS Simple Text to Speech ComfyUI workflow is a compact, practical, and user-friendly solution for generating speech in Videcool. With its combination of a simple node graph, selectable speaker voices, configurable generation settings, and seamless platform integration, it enables beginners and professionals alike to produce narration and spoken audio content quickly and efficiently.