What it is good at
- Expressive long form speech
- Multi speaker
Microsoft · Audio · 3 credits per 1,000 characters
3 credits per 1,000 characters. The exact total is shown above the Generate button before you run it. Failed jobs release their credits automatically.
Narration and dialogue for longer videos. You never have to know the model name to use it. Pick the tool and the outcome, and this engine runs underneath.
These pages sit in the same demand cluster. The order follows real search volume.
Same job, different trade-offs. Every rate below is published and comparable.
3 credits per 1,000 characters. IndexTTS 2 does a similar job for 3 credits.
Less control than a cloned voice. Worth knowing before the first run.
New accounts start with 100 credits, which covers 33 runs on this model.