Voice cloning from a sample
Add a short Reference Audio recording and your text is spoken in that voice.
Clone a voice
Zonos2
Zonos2 is a text-to-speech model that clones a voice from a short sample and speaks naturally across many languages.
Made by Zyphra8 creditsper 5 s Pro
Opens the audio studio with Zonos2 ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What Zonos2 makes, what it needs and what you get
What it makes
Clone a voice
Learns a voice from a short sample so you can reuse it.
What you need
- What the voice should say
Optional: a short sample of the voice.
What you get
A reusable voice that sounds like the sample
About Zonos2
Zonos2, made by Zyphra, clones a voice from a short sample and speaks your text in it. You get back a WAV audio file with your text read in the cloned voice.
Reference Audio is the only required input. It is the recording that the voice is cloned from. Replace the starting sentence in Text with the words you want spoken. Language sets how your text is prepared for speech and starts at US English. Its choices are US English, British English, French, German, Spanish, Italian, Brazilian Portuguese, Japanese, Mandarin Chinese and Korean. Other languages skip that step. Accurate Mode starts on for a closer voice match; turn it off for a more expressive result.
Zonos2 costs about 8 credits for 5s. Zonos-Audio-Clone, from the same maker, costs 100 credits and has no options beyond its Reference Audio and Prompt inputs.
Other models for this job
Same job: clone a voice. Compare before you choose.
Audio Pro Open
Tada TTS 1B Text-to-SpeechClone a voice
A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment. Lighter 1B variant
Hume AI100 creditsper run
Audio Pro Open
Tada Text-to-Speech 3BClone a voice
A unified speech-language model that synchronizes speech and text into a single, cohesive stream via 1:1 alignment.
Open Source100 creditsper run
Audio Pro Open
Zonos-Audio-CloneClone a voice
Clone voice of any person and speak anything in their voice using zonos' voice cloning.
Zyphra100 creditsper run
Audio Pro Open
F5 TTSClone a voice
F5 TTS
Open Source20 creditsper run
What it does well
Closer match or more expressive
Accurate Mode starts on for a closer voice match. Turn it off for a more expressive result.
Text preparation by language
Language sets how your text is prepared for speech. It starts at US English and has choices for British English, French, German, Spanish, Italian, Brazilian Portuguese, Japanese, Mandarin Chinese and Korean. Other languages skip that step.
WAV audio output
You get back a WAV audio file with your text spoken in the cloned voice.
How to use Zonos2
How It Works
How It Works
01
Add your reference audio
Upload a short recording of the voice you want to clone.
02
Enter your text
Replace the starting sentence in Text with the words to speak. Pick a Language and decide whether Accurate Mode stays on.
03
Generate the audio
Run it and play the WAV audio file you get back.
Tip Add one reference recording. Zonos2 accepts one input file.
Good for
Narration in a cloned voice
Read a script aloud in the voice from your recording.
Spoken greetings
Turn a short message into audio in a voice you choose.
Questions
Quick answers to help you get the most out of Zonos2 in FunAI Studio.
1. What do I need to provide?
2. What do I get back?
3. What does Language do?