free-voiceGenerate Russian male voice audio using ComfyUI with Qwen3 TTS node and save as MP3 for voice messages.
Install via ClawdBot CLI:
clawdbot install Onimka/free-voiceНавык для генерации аудио через ComfyUI с использованием узла AILab_Qwen3TTSVoiceDesign_Advanced.
AILab_Qwen3TTSVoiceDesign_AdvancedE:\Ai\Comfy UI\output\ для сохранения аудиоЕсли ComfyUI не запущена, использовать:
cmd /c start "" "C:\Users\user\Desktop\ComfyUI.lnk"
Проверять доступность по http://localhost:8000 каждые 10 секунд до готовности.
{
"prompt": {
"50": {
"inputs": {
"filename_prefix": "qwen3-tts/[UNIQUE_ID]",
"quality": "320k",
"audioUI": "",
"audio": ["55", 0]
},
"class_type": "SaveAudioMP3",
"_meta": {"title": "Сохранить аудио (MP3)"}
},
"55": {
"inputs": {
"text": "[TEXT]",
"instruct": "A male voice with a slightly hoarse, warm tone, speaking in a confident and friendly manner.",
"model_size": "1.7B",
"device": "auto",
"precision": "bf16",
"language": "Russian",
"max_new_tokens": 2048,
"do_sample": true,
"top_p": 0.9,
"top_k": 50,
"temperature": 0.9,
"repetition_penalty": 1,
"unload_models": false,
"seed": -1
},
"class_type": "AILab_Qwen3TTSVoiceDesign_Advanced",
"_meta": {"title": "Qwen3 TTS VoiceDesign (Advanced)"}
}
}
}
http://localhost:8000/promptprompt_id/history/[prompt_id]E:\Ai\Comfy UI\output\[filename_prefix]*.mp3message(asVoice=true)Generated Mar 1, 2026
Generates high-quality Russian audiobooks with a warm male voice, ideal for publishers needing efficient production. It reduces recording costs and time by automating narration for fiction or educational content.
Creates natural-sounding audio responses for AI assistants or chatbots in Russian, enhancing user engagement. Useful for customer service bots or smart home devices requiring localized voice output.
Produces audio lessons or tutorials in Russian for e-learning platforms, supporting language learning or online courses. It allows educators to quickly generate voiceovers without professional recording setups.
Generates voiceovers for commercials or promotional videos in Russian, offering customizable tones for different brand messages. Helps marketers create audio content rapidly for campaigns or social media.
Converts text to speech for visually impaired users or applications needing audio support in Russian. Integrates into websites or apps to provide accessible content through voice output.
Offers a cloud-based TTS service with API access for developers, charging monthly fees based on usage volume. Targets businesses needing scalable audio generation without local setup costs.
Sells credits or tokens for each audio generation request, ideal for occasional users or small projects. Allows flexible pricing and easy integration into existing platforms.
Provides customized TTS packages for enterprises to rebrand and integrate into their products, such as e-learning tools or voice assistants. Includes technical support and customization fees.
💬 Integration Tip
Ensure ComfyUI is running and accessible via localhost before sending requests, and monitor the output folder for generated MP3 files to handle errors gracefully.
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Local Voice Input/Output for Agents using the AI Voice Agent API.
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
本地生成 Telegram 语音消息,支持自动清洗、分段与临时文件管理。
Speak responses aloud on macOS using the built-in `say` command when user input indicates Voice Wake/voice recognition (for example, messages starting with "User talked via voice recognition on <device>").
向指定 Telegram 群组发送语音消息