Voice conversion
Voice conversion changes the sound of live speech.
Part of Communication methods.
How it works
The creator talks, and software transforms the audio into a different voice in real time.
- Input: Live speech into a microphone.
- Processing: The audio itself is transformed, so the words stay the same and only the voice changes. TTS starts from text, while voice conversion starts from speech (overview of voice conversion research).
- Delivery: The creator’s own timing and phrasing in a different voice.
Viewers get live conversation with the rhythm of ordinary talk.
What it isn’t
Voice conversion works from the speech itself and doesn’t need a transcript for a voice to read, so it is a separate method from TTS even though both change what viewers hear. Speech-to-text-to-speech also starts with speech, but it transcribes the words and has a synthetic voice read them. Products sold as voice changers may use voice conversion or simpler effects such as pitch shifting.
Before you stream with it
Listen back to a test recording. Check that only the converted voice reaches the stream, and that the delay feels natural in conversation.
Questions
- Is a voice changer the same as voice conversion?
- On Voice Protocol, voice changers are listed under this method. Technically, voice conversion is one approach behind them, remapping your speech to a different voice. Other voice changers use simpler effects such as pitch shifting.
- Is voice conversion TTS?
- No. They can sound alike, but TTS starts from text and voice conversion starts from speech.
Read more: What is a TTS VTuber?
Creators who use voice conversion
A listing shows how a creator communicates, not why.
No creators are listed for voice conversion yet. Stream with it? Share your protocol