Features · Voice-overs
A voice, a speed.
Say it in your words.
The composer.
Write what to say. Choose English, German or Dutch, a voice, a speed from 0.5 to 2 and an emotion: neutral, warm, cheerful, calm, serious or excited. Choose one to four takes. The composer shows the credits and names the model that will make it.
- 1 credit per 500 characters, times the takes
- Making sound needs Premium or Max
- Preview voices: Ava, Ben, Noor, Max, Robo
Be clear about this
The Preview voice.
- Pre-betaA robot voice
The Preview voice is synthesised in your browser from a glottal pulse through vowel formants, with pitch from the voice, contour from the emotion and rate from the speed. It is intelligible and robotic, not natural.
- Pre-betaReal voices need a key
Gemini speech, ElevenLabs voices and an optional OpenAI voice are connected in code for single voices and work where their keys are set.
Questions
About voice-overs.
Will the voice sound human?
Not with the Preview: it is a robot voice. A real voice model may, where one is switched on.
What can I make?
Four kinds: voice-over, music bed, sound effect and two-voice dialogue.
Which languages?
English, German and Dutch for speech.