Zonos2

Zonos2

Playground

Zonos2 is a fast multilingual voice-cloning text-to-speech model that generates natural speech from text using a short reference audio sample. Ready-to-use REST inference API for voice cloning, multilingual TTS, narration, dubbing, character dialogue, virtual assistants, creator content, and professional speech generation workflows with simple integration, no coldstarts, and affordable pricing.

Features

Zonos2 Voice Cloning Text-to-Speech

Zonos2 Voice Cloning Text-to-Speech is an open-source, real-time text-to-speech model from Zyphra. It clones a voice from a short reference audio sample and synthesizes the supplied text in the cloned voice.

Why Choose This?

• Voice cloning from reference audio
  Clone a speaker’s voice from a short audio sample and generate speech from text.

• Real-time text-to-speech model
  Built on Zonos2, an open-source real-time TTS model from Zyphra.

• Background cleanup option
  Use clean_speaker_background when the reference audio has a clean background.

• Standard audio output
  The generated audio is returned as a URL in the standard WaveSpeed prediction response.

Parameters

How to Use

1. Upload reference audio — Provide a short, clear audio sample of the speaker voice you want to clone.
2. Enter text — Provide the text that should be spoken in the cloned voice.
3. Set background option (optional) — Enable clean_speaker_background when the reference audio has a clean background.
4. Submit — Generate the cloned-voice speech output.

Output

Returns generated audio URL(s) in the standard WaveSpeed prediction response.

The generated audio is returned as WAV, 44.1kHz mono.

Pricing

Pricing is $0.01 per minute.

Billing Rules

• Billing is based on the reference audio duration.
• Reference audio duration is rounded up to the next full minute.
• Minimum billing duration is 1 minute.
• Each billed minute costs $0.01.

Best Use Cases

• Voice cloning TTS — Generate speech in a cloned voice from a reference audio sample.
• Narration generation — Create spoken narration from text using a target speaker voice.
• Dialogue prototyping — Test voice lines, character speech, or script variations.
• Localized speech generation — Use supported language normalization codes for multilingual text handling.
• Audio content creation — Generate voice audio for videos, demos, apps, or creative workflows.

Pro Tips

• Use clean reference audio with minimal background noise for better cloning quality.
• Use a short and clear speaker sample for more stable voice cloning.
• Make sure the reference audio contains the target speaker clearly.
• Enable clean_speaker_background only when the reference audio has a clean background.
• Ensure the audio URL is publicly accessible.

Notes

• audio and text are required fields.
• Provider sampling settings use the default mapping values.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/zonos2" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "clean_speaker_background": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"