Qwen3-TTS-VoiceDesign — Speech AI Model
Qwen3-TTS VoiceDesign: on-device text-to-speech with a voice you describe in words. No API key.
Details
- CategorySpeech
- Year2026
- LicenseApache-2.0
Compliance & Provenance
- ProviderAlibaba (open weights) · Specialized
- EU AI Act RiskLimited Risk
- Art. 50 TransparencyRequired — AI-generated outputs are marked
Inputs & Outputs
- TextInputstring
Text to speak (the script)
- Voice DescriptionInputstringoptional
Optional description of the voice; overrides the Voice description setting when connected
- SoundOutputsound
Synthesized voiceover audio (WAV)
Parameters
- voice_descriptionstringdefault A warm, friendly young adult woman with…
Describe the voice in English, e.g. a warm young American woman, upbeat. The spoken language follows the text.
Natural-language description of the voice: age, gender, accent, tone, pace (max 500 characters). Write it in English even when the script is Korean or another language: the model follows English descriptions more reliably (the same voice described in Korean came out quieter and slower), and the spoken language comes from the text and the language setting, not from the description. Ignored when the Voice Description port is connected. Empty uses a fixed neutral adult voice.
- languagestringdefault Autooptions: Auto, Korean, Englishadvanced
Spoken language hint (Auto follows the text).
- speedfloatdefault 1range 0.5–2
Speaking speed. 1.0 = as generated; >1 faster, <1 slower. Pitch is kept.
Playback speed of the synthesized voice, 0.5-2.0 (default 1.0). The audio is re-timed after synthesis with its pitch kept, so 1.1 means exactly 10% faster. Values outside the range are clamped.
- pronunciationsstringdefault advanced
Respell words the voice misreads: written=spoken, separated by ; or new lines, e.g. cnaps.ai=see-naps dot A I.
Pronunciation rules applied only to the text sent to the voice model: written=spoken entries separated by ';' or new lines, e.g. `cnaps.ai=see-naps dot A I; cnaps=see-naps`. Matching is case-insensitive and whole-word: an English letter or digit directly before or after a written form that starts or ends with one blocks the match (cnaps never fires inside cnapsule), and a written form starting with Hangul must not follow another letter (a rule for 냅스 does not touch 씨냅스). Korean particles may follow directly: cnaps.ai에서 and 씨냅스는 both match. Longer written forms win over shorter ones and replaced text is not re-scanned. Max 50 rules and 2000 characters; a rule without '=' or with an empty side fails the run. Captions should come from the original script (feed the same script to Whisper's Script port), not the respelled text.
- loudnessstringdefault -16 LUFSoptions: off, -14 LUFS, -16 LUFS, -20 LUFSadvanced
Normalize the voice to a fixed loudness. off keeps the level as generated.
Loudness normalization after synthesis and the speed change (ffmpeg loudnorm, single pass, true peak -1.5 dBTP). 'off' keeps the level as generated; '-14 LUFS' is loud (social/streaming), '-16 LUFS' the usual voiceover level, '-20 LUFS' quieter, leaving headroom for music. Default -16 LUFS here because the VoiceDesign output level varies with the voice description.
Tags
Alternatives in Audio Models
- Music (Lyria)
Google Lyria: text (and optional image) to music — full songs with vocals and lyrics, or 30-second clips. Needs API key.
- Text to Music (ACE-Step 1.5)
ACE-Step 1.5: generate music from a style prompt, with optional lyrics, key, tempo and time signature. 48 kHz stereo, 5-600s.
- Text to Sound Effect (MOSS-SoundEffect v2)
MOSS-SoundEffect v2.0: generate a sound effect from an English description. 48 kHz mono, 0.5-30s.
- Text to Speech (Gemini)
Google Gemini TTS: turn text into a spoken voiceover (Korean/English). Needs API key.
- Text to Speech (Qwen3)
Qwen3-TTS: on-device text-to-speech voiceover (Korean/English). No API key.