manyframeQwen3 TTS Flash.
Give a short script a voice. Prepare narration for a visual idea with a selected voice supported by the configured model route.
Available models and settings are shown in your studio. Review the quote before generating.
The route.
The right inputs.
Start from the creative job, then choose the model and settings that fit it.
Model ID qwen3-tts-flash
- Script limit
- Non-empty text, at most 600 characters.
- Voice
- Required voice ID supported by the selected model.
- Delivery instructions
- Not accepted on this route; use the Instruct Flash model for that field.
- Output
- Speech audio; check current route and exposed audio settings in studio.
Capabilities describe the Manyframe connector. Your studio shows the currently enabled route, supported settings and maximum charge.
Write for the ear.
A good voice track starts with a script that sounds natural when read aloud. Use short sentences, leave room for the listener to understand the product and keep the message proportionate to the accompanying visual.
The connector requires a supported voice ID; it does not establish arbitrary voice cloning or a universal voice list. Listen for pronunciation, pace and clarity before adding the audio to a campaign edit.
This route does not accept delivery instructions. For supported text guidance on the performance, review Qwen3 TTS Instruct Flash. To animate a permitted image with prepared speech, explore the separate Wan S2V route.
Good questions. Clear answers.
Still curious? Browse all FAQs
Can I paste a long article?
The connector accepts at most 600 characters per speech request. Prepare a concise script rather than assuming a long-document narration workflow.
Can I ask this model to speak in a particular emotional style?
The instructions field is not supported by this exact route. The separate Qwen3 TTS Instruct Flash connector accepts delivery instructions.
Can I use any named voice?
Choose a voice supported by the selected model and current configured route. The connector requires a voice ID but does not prove arbitrary voice cloning or impersonation support.
Make the words easy to hear.
Available models and settings are shown in your studio. Choose a supported voice and review the quote.