AudioLive
LiveMiniMax Voice Clone
Clone a speaking voice from one reference recording, then use the reusable voice ID with MiniMax Turbo or HD speech models.
Audio → voice ID
$0.65 / cloneLiveMiniMax + Suno2 models
Voice Cloning API — Clone a Voice for Speech or Music
Muapi's voice cloning API turns a short reference recording into a reusable voice ID through one unified REST workflow. Use MiniMax Voice Clone for speaking voices that feed MiniMax text-to-speech models, or Suno Custom Voice Cloning for singing voices used in music generation. Create the clone once, then reuse the identifier across future requests.
Live voice-cloning modelsSpeaking and singing voice identities2 models
Try Model
AudioPreview
LiveSuno Custom Voice Cloning
Clone a singing voice through a two-take flow with a fresh liveness phrase, then use the resulting voice persona in Suno music generation.
Audio → voice ID
Free previewWhat is a Voice Cloning API?
A voice cloning API analyzes a short audio sample and creates a reusable voice identity. Instead of uploading the same reference clip every time, you create a voice once and pass its voice ID into later speech or music generation requests.
Muapi exposes two different cloning workflows. MiniMax Voice Clone creates a speaking voice for MiniMax text-to-speech models; Suno Custom Voice Cloning creates a singing persona for Suno music generation, remix, and extend workflows.
Both start with an audio URL and use Muapi's asynchronous submit-and-poll pattern. Suno adds a second confirmation request because the speaker must read a fresh phrase generated for that clone.
Voice Cloning API capabilities
Speaking voice clones
MiniMax reproduces tone, accent, rhythm, emotion, and speaking style from a reference recording.
Reusable MiniMax voice IDs
Use a cloned MiniMax voice with speech-02-hd, speech-02-turbo, speech-2.5, or speech-2.6 HD and Turbo models.
Singing voice personas
Suno Custom Voice Cloning captures a singing voice for music generation, remix, and extend requests.
Liveness verification
Suno requires a fresh random phrase to be read after the sample, helping prevent cloning from a static recording without the speaker present.
Input cleanup controls
MiniMax supports optional noise reduction and volume normalization for cleaner clones from imperfect recordings.
Named custom voices
Set a custom_voice_id for MiniMax or voice_name and style metadata for Suno so your voice library stays organized.
Voice cloning use cases
Personalized narration
Create a consistent voice for product videos, courses, podcasts, and interactive experiences.
Character and dialogue pipelines
Reuse a speaking voice across scenes, languages, and automated text-to-speech generations.
Singing demos and music
Build a reusable vocal persona for Suno songs, remixes, and extended arrangements.
Voice Cloning Model Comparison
| Model | Provider | Price | Best For |
|---|---|---|---|
| MiniMax Voice Clone | MiniMax | $0.65 / clone | Speaking voice for text-to-speech narration and dialogue |
| Suno Custom Voice Cloning | Suno | Free preview | Singing voice persona for Suno music generation |
Voice Cloning API code examples
Start with a reference audio URL, poll the returned request ID, and follow the model-specific completion flow. Suno requires a confirmation recording after its liveness phrase.
1. Clone a speaking voice with MiniMax
curl -X POST https://api.muapi.ai/api/v1/minimax-voice-clone -H "x-api-key: YOUR_API_KEY" -H "Content-Type: application/json" -d '{"audio_url":"https://example.com/voice-sample.wav","custom_voice_id":"myvoice001","model":"speech-02-hd","need_noise_reduction":true,"need_volume_normalization":true,"accuracy":0.7,"prompt":"Welcome to Muapi."}'
# Response: {"request_id":"REQUEST_ID"}
curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result -H "x-api-key: YOUR_API_KEY"Send a reference audio URL and custom_voice_id. Optional noise reduction, normalization, accuracy, model, and preview prompt fields are shown in the request.
2. Clone a singing voice with Suno
curl -X POST https://api.muapi.ai/api/v1/suno-voice-clone -H "x-api-key: YOUR_API_KEY" -H "Content-Type: application/json" -d '{"audio_url":"https://example.com/singing-sample.wav","voice_name":"My Voice","language":"en","style":"Pop, Female Vocal"}'
# Poll until stage is "awaiting_phrase", then read the returned phrase aloud.
curl -X POST https://api.muapi.ai/api/v1/suno-voice-clone/REQUEST_ID/confirm -H "x-api-key: YOUR_API_KEY" -H "Content-Type: application/json" -d '{"audio_url":"https://example.com/verification-phrase.wav"}'
# Poll /predictions/REQUEST_ID/result again until voice_id is available.Submit the sample first, read the fresh phrase returned at awaiting_phrase, confirm with the second recording, and poll again until voice_id is available.
Voice Cloning API FAQ
What is a Voice Cloning API?
A voice cloning API turns a short reference recording into a reusable voice ID. MiniMax Voice Clone is for speaking voices and Suno Custom Voice Cloning is for singing voices used in music generation.
Can I use a MiniMax cloned voice with every MiniMax speech model?
Yes. A MiniMax voice ID can be reused with the MiniMax Turbo and HD speech models, including speech-02-hd, speech-02-turbo, speech-2.5 HD/Turbo, and speech-2.6 HD/Turbo.
Why does Suno require a second recording?
Suno generates a fresh phrase after the initial sample. The speaker must read that phrase aloud and submit it as confirmation, which adds a liveness check against cloning from a static recording.
How much does voice cloning cost?
MiniMax Voice Clone costs $0.65 per clone. Suno Custom Voice Cloning is free during its preview period and may change to paid billing later.
Can I clone a voice for singing rather than speech?
Yes. Use Suno Custom Voice Cloning for a singing persona that can be passed into supported Suno music generation, remix, and extend requests.
What recording should I use?
Use a clear recording with the target speaker's voice prominent and minimal noise. Suno's initial sample is designed for about 10 seconds, followed by its generated verification phrase.
How do I get Voice Cloning API access?
Create a Muapi account, generate an API key from the dashboard, and call the MiniMax or Suno voice-cloning endpoint. There is no waitlist.
Text to Speech API →Use a cloned speaking voice to generate narration and dialogue.Suno Music API →Use a cloned singing persona in Suno music workflows.AI Audio & Music API →Browse speech, music, sound effects, and voice tools.
Ready to create a reusable voice?
Create one API key and choose MiniMax for speech or Suno for singing.