Emotion / Style
Speed
Speed
1.0×
Text Input
Custom Style Instruction (optional — overrides emotion/accent/speed presets)
⚙️ Advanced sampling ▾
⚠️ Voice Clone backend is not ready. https://tts-qwen3-base.ai.apibox.link
Reference Audio (upload a voice sample)
🎵
Click or drag & drop an audio file here
Supports WAV, MP3, FLAC, OGG
Reference Transcript * required in Full Clone mode — what the reference audio says
Language of Reference Audio
Auto-detect
English Spanish Portuguese French German Italian
Chinese Japanese
Korean Hindi
Indonesian Thai
Vietnamese
Arabic Russian
Turkish Dutch
Polish Swedish
Mode
Full Clone (voice + style)
X-Vector Only (voice timbre only)
Text to Synthesize
⚠️ Voice Design not supported by this model. tts_model_type: base) only supports Voice Clone.generate_voice_design capability.
🎛 Voice Builder
Gender
♂ Male
♀ Female
◎ Neutral
Age
Young (20s)
Adult (30s)
Mature (50+)
Language / Country
🇺🇸 English — United States
🇬🇧 English — United Kingdom
🇦🇺 English — Australia
🇨🇦 English — Canada
🇮🇳 English — India
🇿🇦 English — South Africa
🇲🇽 Spanish — Mexico
🇪🇸 Spanish — Spain (Castilian)
🇨🇴 Spanish — Colombia
🇦🇷 Spanish — Argentina
🇨🇱 Spanish — Chile
🇻🇪 Spanish — Venezuela
🇧🇷 Portuguese — Brazil
🇵🇹 Portuguese — Portugal
🇫🇷 French — France
🇨🇦 French — Canada
🇩🇪 German — Germany
🇦🇹 German — Austria
🇮🇹 Italian — Italy
🇨🇳 Chinese — Mandarin (Mainland)
🇹🇼 Chinese — Mandarin (Taiwan)
🇯🇵 Japanese — Japan
🇰🇷 Korean — Korea
🇮🇳 Hindi — India
🇮🇩 Indonesian — Indonesia
🇹🇭 Thai — Thailand
🇻🇳 Vietnamese — Vietnam
🇸🇦 Arabic — Saudi Arabia
🇪🇬 Arabic — Egypt
🇹🇷 Turkish — Turkey
🇷🇺 Russian — Russia
🇳🇱 Dutch — Netherlands
🇵🇱 Polish — Poland
🇸🇪 Swedish — Sweden
🇳🇴 Norwegian — Norway
🇩🇰 Danish — Denmark
🇫🇮 Finnish — Finland
Tone
💼 Professional
🤗 Warm
⚡ Energetic
🌊 Calm
🎯 Authoritative
😄 Cheerful
📖 Narrative
Generated Voice Description
…
Override / Add Details (optional)
Text to Synthesize