#VoiceDesign
Qwen3-TTS enables custom voices via voice embeddings, but instruction-based control is limited for base cloning, requiring fine-tuning or VoiceDesign-to-Base workflows.
Save What Matters
Curate Feeds | Make Collections | Customize Email Briefs
briefly.co
October 29, 2026 at 8:14 PM
Qwen3-TTS enables custom voices via voice embeddings, but instruction-based control is limited for base cloning, requiring fine-tuning or VoiceDesign-to-Base workflows.
Save What Matters
Curate Feeds | Make Collections | Customize Email Briefs
briefly.co
October 29, 2026 at 8:12 PM
Qwen3-TTS enables custom voices via voice embeddings, but instruction-based control is limited for base cloning, requiring fine-tuning or VoiceDesign-to-Base workflows.
Save What Matters
Curate Feeds | Make Collections | Customize Email Briefs
briefly.co
October 29, 2026 at 8:14 PM
Qwen3-TTS enables custom voices via voice embeddings, but instruction-based control is limited for base cloning, requiring fine-tuning or VoiceDesign-to-Base workflows.
Save What Matters
Curate Feeds | Make Collections | Customize Email Briefs
briefly.co
October 29, 2026 at 8:12 PM
La entrada incluye instrucciones muy detalladas para ejecutarlo, bastan con ~8GB de VRAM e incluye una web de demo para probarlo en local cómodamente.
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 22, 2026 at 9:53 PM
Qwen just released Qwen3-TTS 🔊

huggingface.co/collections/...

✨ VoiceDesign, CustomVoice & Base : from custom voices to rapid voice cloning 🎙️
✨ 0.6B & 1.7B - Apache2.0
✨ 10 language support
✨ SOTA 12 Hz speech tokenizer for high compression & high-fidelity audio
Qwen3-TTS - a Qwen Collection
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 22, 2026 at 2:41 PM
🎭🔊 مرّة واحدة تكفي لتغيّر شكل محتواك الصوتي للأبد.
تخيّل أن عندك القدرة إنك تصمّم صوت من الصفر… تحدد نبرته، إيقاعه، مزاجه، شخصيته، وتستنسخه في ثواني… مش من شركة دبلجة، بل من نموذج ذكاء اصطناعي جاهز يخدمك أنت ومشروعك.

#حسام_الدين_حسن #خبير_اونلاين
#Qwen3 #Qwen3_TTS #VoiceDesign #VoiceClone
December 25, 2025 at 6:41 PM
Runs Qwen3-TTS models in ComfyUI via custom nodes for CustomVoice, VoiceDesign, and VoiceClone.
July 31, 2026 at 5:34 AM
でも同じGitHubには、学習用のmanifest準備、speaker/caption列、2段階訓練まで並んでる。Colab版も「ランタイムをGPUに変更」から始まる。確認できた範囲では、「ほぼ放置で完成」より「声づくりの入口がかなり広がった」が近い。Colab:https://github.com/shinshin86/Irodori-TTS-600M-v3-VoiceDesign-with-colab
June 26, 2026 at 7:54 PM
一次ソースを読むと、Irodori-TTS v3 VoiceDesignが text + reference speech + caption text の3要素制御なのは確認できた。参照音声で声を寄せつつ、キャプションで話し方を動かせる。ここはかなり本当。公式:https://huggingface.co/Aratako/Irodori-TTS-600M-v3-VoiceDesign GitHub:https://github.com/Aratako/Irodori-TTS
June 26, 2026 at 7:54 PM
「ほぼ放置でオリジナル音声」、その一言だけ少し速い。紹介ポストは、Claude Codeにベース音声を渡して、Irodori-TTS VoiceDesign V3で雰囲気を寄せ、そのまま学習データ量産まで行ける、という話。紹介:https://x.com/shinshin86/status/2061797074816123017
June 26, 2026 at 7:54 PM
v1から順当なバージョンアップ。VoiceDesignも良いね。

「Irodori-TTS v3」「Irodori-TTS v2 VoiceDesign」を試す
zenn.dev/kun432/scrap...
「Irodori-TTS v3」「Irodori-TTS v2 VoiceDesign」を試す
kun432さんのスクラップ
zenn.dev
May 18, 2026 at 4:45 AM
Let any text speak - with open-source
Open-source text-to-speech powered by QWEN3-TTS **→ The app is already online. You can try it at anyspeak.ai and check repo on anyspeak-ai · GitHub ** Features * **TTS:** Multiple voices and Qwen3-TTS models (1.7B CustomVoice, VoiceDesign, Base). Supported languages: Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish. * **Speaker tags:** Use `[SPEAKER_NAME]` in text for multi-speaker output. * **Mood tags:** Use `[SPEAKER:mood]` (e.g. `[VIVIAN:happy]`) for emotional expressiveness. * **Timing tags:** Use `[SPEAKER:mood:timing]` (e.g. `[RYAN:+1.5]` for 1.5 s pause after, `[VIVIAN:happy:-0.3]` for shorter gap or even speaker overlapping) or the + TIMING button to control pacing between segments. * **Custom voices:** Voice Design by selecting attributes (gender, language, old/young, slow/fast, high/low, loud/soft, warm/rough). * **CLEAN:** Analyze and clean text for better TTS output. * **CHECK:** Quality check with Whisper (compare original vs. synthesized). * **IMPROVE:** Post-process generated audio by chunk: selectively regenerate mispronounced segments, trim silence, add pauses, or edit text and re-generate. Compare original vs. improved before applying. You can also edit finished MP3s afterward (e.g. different wording or different speaker at a specific place) without regenerating everything. * **VIDEO:** Create video from audio and images (with optional subtitles). * **Load & Save (MP3):** Load and save via MP3. Very powerful: you can continue working at the same place, and files store the original text with tags in their metadata. * **Import:** Load text from URL or file. * Run local - easy installation
discuss.huggingface.co
February 21, 2026 at 10:36 PM
Let any text speak - with open-source
Open-source text-to-speech powered by QWEN3-TTS **→ The app is already online. You can try it at anyspeak.ai and check repo on anyspeak-ai · GitHub ** Features * **TTS:** Multiple voices and Qwen3-TTS models (1.7B CustomVoice, VoiceDesign, Base). Supported languages: Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish. * **Speaker tags:** Use `[SPEAKER_NAME]` in text for multi-speaker output. * **Mood tags:** Use `[SPEAKER:mood]` (e.g. `[VIVIAN:happy]`) for emotional expressiveness. * **Timing tags:** Use `[SPEAKER:mood:timing]` (e.g. `[RYAN:+1.5]` for 1.5 s pause after, `[VIVIAN:happy:-0.3]` for shorter gap or even speaker overlapping) or the + TIMING button to control pacing between segments. * **Custom voices:** Voice Design by selecting attributes (gender, language, old/young, slow/fast, high/low, loud/soft, warm/rough). * **CLEAN:** Analyze and clean text for better TTS output. * **CHECK:** Quality check with Whisper (compare original vs. synthesized). * **IMPROVE:** Post-process generated audio by chunk: selectively regenerate mispronounced segments, trim silence, add pauses, or edit text and re-generate. Compare original vs. improved before applying. You can also edit finished MP3s afterward (e.g. different wording or different speaker at a specific place) without regenerating everything. * **VIDEO:** Create video from audio and images (with optional subtitles). * **Load & Save (MP3):** Load and save via MP3. Very powerful: you can continue working at the same place, and files store the original text with tags in their metadata. * **Import:** Load text from URL or file. * Run local - easy installation
discuss.huggingface.co
February 21, 2026 at 7:35 AM
Let any text speak - with open-source
Open-source text-to-speech powered by QWEN3-TTS **→ The app is already online. You can try it at anyspeak.ai and check repo on anyspeak-ai · GitHub ** Features * **TTS:** Multiple voices and Qwen3-TTS models (1.7B CustomVoice, VoiceDesign, Base). Supported languages: Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish. * **Speaker tags:** Use `[SPEAKER_NAME]` in text for multi-speaker output. * **Mood tags:** Use `[SPEAKER:mood]` (e.g. `[VIVIAN:happy]`) for emotional expressiveness. * **Timing tags:** Use `[SPEAKER:mood:timing]` (e.g. `[RYAN:+1.5]` for 1.5 s pause after, `[VIVIAN:happy:-0.3]` for shorter gap or even speaker overlapping) or the + TIMING button to control pacing between segments. * **Custom voices:** Voice Design by selecting attributes (gender, language, old/young, slow/fast, high/low, loud/soft, warm/rough). * **CLEAN:** Analyze and clean text for better TTS output. * **CHECK:** Quality check with Whisper (compare original vs. synthesized). * **IMPROVE:** Post-process generated audio by chunk: selectively regenerate mispronounced segments, trim silence, add pauses, or edit text and re-generate. Compare original vs. improved before applying. You can also edit finished MP3s afterward (e.g. different wording or different speaker at a specific place) without regenerating everything. * **VIDEO:** Create video from audio and images (with optional subtitles). * **Load & Save (MP3):** Load and save via MP3. Very powerful: you can continue working at the same place, and files store the original text with tags in their metadata. * **Import:** Load text from URL or file. * Run local - easy installation
discuss.huggingface.co
February 21, 2026 at 1:34 AM
Alibaba Just Dropped Three Game-Changing AI Models – Here’s What They Do

Alibaba unveiled a triple threat in late December 2025: Fun-Audio-Chat-8B, an open-source speech-to-speech model with emotion-aware capabilities; Qwen-Image-Edit-2511, a major upgrade for consistent image editing; and…
Alibaba Just Dropped Three Game-Changing AI Models – Here’s What They Do
Alibaba unveiled a triple threat in late December 2025: Fun-Audio-Chat-8B, an open-source speech-to-speech model with emotion-aware capabilities; Qwen-Image-Edit-2511, a major upgrade for consistent image editing; and VoiceDesign-VD-Flash, a controllable text-to-speech system that takes natural language instructions. These releases mark a significant shift in how developers can access frontier-level AI capabilities without proprietary restrictions, challenging closed-source models from OpenAI and Google.
www.adwaitx.com
December 31, 2025 at 7:44 PM
Hey voice editors: Why are we in a rush? I understand retention time gets rewarded through ads, but have we compromised a normal life because of it? Why are all interviews edited to remove pauses?

1/5

#postproduction #voicedesign #sounddesign #podcasts
November 27, 2025 at 11:24 AM
Qwen3-TTS is officially live. We’ve open-sourced the full family—VoiceDesign, CustomVoice, and Base—bringing high quality to the open community.

- 5 models (0.6B & 1.8B)
- Free-form voice design & cloning
- Support for 10 languages
- Full fine-tuning support
github.com
January 22, 2026 at 9:29 PM
Créez votre voix IA sur mesure avec ElevenLabs

👉 Tester gratuitement : https://try.elevenlabs.io/tv8kdcaax8a1

Parce qu’avoir la bonne voix au bon moment, c’est décisif pour vos récits, vos produits, vos personnages.

#VoiceDesign #VoixIA #GénérateurDeVoix #CréationAudio #ClonageVocal #NarrationIA…
Créer sa voix IA avec Voice Design v3
Voice Design v3 d’ElevenLabs permet de créer une voix IA personnalisée en décrivant simplement son timbre, son âge ou son accent.
kingland.fr
November 2, 2025 at 9:28 AM
youtube.com
November 22, 2024 at 4:45 PM
If someone can’t use their hands, how does your product adapt?

www.instagram.com/p/DM97wTzoO22/

#UX #InclusiveDesign #MobileFriendly #Accessibility #A11y #VoiceDesign
August 5, 2025 at 9:18 AM
Chilling Allan Wake 2 horror #voicedesign tutorial by Agustin Chavarria 🔪 👀! www.linkedin.com/feed/update/...
Agustin Chavarria on LinkedIn: #sounddesign #alanwake2 #gameaudio
I recently completed a sound design assignment at School of Video Game Audio I took the opportunity to revisit my work on the Alan Wake 2 intro and crafted…
www.linkedin.com
February 15, 2024 at 3:28 PM
Qwen3-TTS (open-weight) - It's like ElevenLabs, but you don't have to pay them.

They have released the full family—VoiceDesign, CustomVoice, and Base—bringing high quality to the open community.

- 5 models (0.6B & 1.8B)
- Free-form voice design & cloning
- Support for 10 languages
January 23, 2026 at 2:10 PM