

Generate speech from text
Add Qwen3 TTS 1.7B to a audio node and generate speech from text without leaving your canvas.
Frequently asked questions
What is Qwen3 TTS 1.7B?
Qwen3 TTS 1.7B turns written text into spoken audio. Use it on an audio node to create narration or compare delivery with the other speech models in your canvas.
How do I use Qwen3 TTS 1.7B on Melius?
Melius is a node-based canvas: add a audio node, pick Qwen3 TTS 1.7B from the model picker, and connect it to whatever should feed it or follow it. You only pay for what you generate.
Explore other models
ElevenLabs Scribe v2
Sonilo Video Sound EffectsSonilo Video Sound Effects
Sonilo Sound EffectsSonilo Sound Effects
xAI TTS v1xAI TTS v1
MiniMax Speech 2.8 HDMiniMax Speech 2.8 HD
Gemini 3.1 Flash TTSGemini 3.1 Flash TTS
Fish Audio S2.1 ProFish Audio S2.1 Pro
ElevenLabs Turbo v2.5ElevenLabs Turbo v2.5
