Qwen3 TTS

Name: Qwen3 TTS
Author: Nodespell Team

Official

Synthesize speech with Qwen3 TTS using preset voices, voice cloning, or voice design.

Nodespell AI

AI / Audio / Qwen

Synthesize speech with Qwen3 TTS using preset voices, voice cloning, or voice design.

Use this for narration, character tests, temp voiceover, or multilingual speech drafts when a single node should cover several voice-generation modes.

Inputs (2)

Text

String

Text to synthesize into speech.

RequiredMulti InputMin: 0Max: 100

Reference Audio

String

Reference audio for voice cloning mode.

Min: 0Max: 100

Parameters (7)

Text

String

Text to synthesize into speech.

Required

Default:

Mode

String

TTS mode: preset voice, voice clone, or voice design.

Default: custom_voice

Language

String

Language of the text. Auto detects the language.

Default: auto

Speaker

String

Preset speaker voice for preset-voice mode.

Default: Serena

Voice Description

String

Natural-language description of the desired voice for voice-design mode.

Default:

Reference Text

String

Transcript of the reference audio for voice-clone mode.

Default:

Style Instruction

String

Optional emotion, pacing, or speaking style instruction.

Default:

Outputs (1)

Output

Inferred

Generated audio output.

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Keywords

Text To SpeechVoice CloningMultimodal Generation

Use in Workflow