# AI Voice Cloning AudioPod clones a voice from 5–60 seconds of clean speech: record or upload a reference in Voice Studio and the AudioSonic engine turns it into a custom voice that can speak 200+ languages. Basic (free) keeps 3 custom voices; Creator and above keep unlimited. Canonical URL: https://audiopod.ai/features/voice-cloning Last updated: 2026-10-14 ## Facts | Fact | Detail | | --- | --- | | Reference recording | 5–60 seconds each, up to 5 recordings | | File size | Up to 10 MB per recording | | How to add it | Record in the browser from a sample script, or upload a file | | Sample languages | The reference can be in any of 23 languages | | Languages the clone speaks | 200+ languages | | Engine | AudioSonic, AudioPod's voice engine | | Custom voices you can keep | Basic: 3 · Creator, Pro, Studio: unlimited | | Cost to create a clone | No credits — a clone uses one custom-voice slot | | Cost to speak with it | 500 credits per 1,000 characters (minimum 10 per take) | | Visibility | Private by default; share to Community Voices only with a consent check | | API | POST /api/v1/voice/voice-clone · MCP tool clone_voice | ## How to do it 1. Open Voice Studio and start a new voice. 2. Record yourself reading the sample script, or upload 5–60 seconds of clean speech (up to 5 takes; the clearest is used). 3. Name the voice and keep it private, or share it with the community after the consent check. 4. Wait for the clone to finish, then pick it in Text to Speech, Audiobook Studio or the Voice Changer. 5. Generate speech; each take costs 500 credits per 1,000 characters. ## What makes a good reference recording A short clean sample beats a long noisy one. Anything in the recording becomes part of the voice. - One person, speaking alone. Any second voice in the recording — an interviewer, a laugh off-mic — is material the clone will try to reproduce. - A quiet room. Background hiss, traffic and air conditioning are part of the voice as far as the clone is concerned, and there is no later setting that removes them. - Natural speech, not performance. Read something ordinary at your ordinary pace; a sample recorded in a character voice produces a clone that can only do that character. - No music, no processing, no reverb. Anything printed onto the recording is printed onto the clone. - Consistent distance from the microphone. A sample where you drift closer and further teaches the clone an inconsistency it will keep. ## Consent comes first You may only clone a voice you have the right to use — your own, or someone else's with their explicit, informed permission. Nothing about the upload can verify whose voice it is, so this is entirely on you. - Your own voice needs no one else's permission. - Someone else's voice needs their explicit permission to be cloned, not just to be recorded. - Sharing a clone to Community Voices asks you to confirm that you recorded it yourself or have the speaker's permission. - Agents calling the clone_voice MCP tool must confirm consent, and requests to clone a public figure are declined. ## When not to clone - You want a voice that sounds professional: The catalogue already holds 500+ voices recorded and tuned for exactly that. A clone of your own untrained reading will not beat them, and you will spend the slot finding out. - You want a particular accent or age: Filter the catalogue. Cloning is for reproducing ONE specific person; it is a poor way to shop for a general quality, because you have to find a person with that quality first. - You want a different emotion from a voice you like: Direct it. A bracketed direction changes the performance of any catalogue voice, and it costs nothing to try again — where a clone bakes whatever mood you recorded into every line it will ever read. - You want to sound like a famous performer: Do not. It is their voice, it is usually their income, and the fact that a clean recording is easy to find is not a permission — see the consent rule. - You have only a noisy or crowded recording: Record five clean seconds on a phone in a quiet room instead. A short clean sample beats a long dirty one, and the noise in a dirty sample becomes part of the voice permanently. ## FAQ **How much audio do I need to clone a voice?** Between 5 and 60 seconds per recording, at most 10 MB. You can add up to 5 recordings and AudioPod uses your clearest take. Clean, natural speech in a quiet room matters more than length. **Is voice cloning free?** Yes, on the free Basic plan: cloning is not locked behind a paid plan, but Basic keeps 3 custom voices at a time and includes 5,000 credits a month — about 10,000 characters of speech. Creator and above keep unlimited custom voices. See /pricing for plan prices. **What does it cost to use a cloned voice?** Creating the clone uses no credits. Speech made with it is billed like any text to speech: 500 credits per 1,000 characters, with a minimum of 10 credits per take. Creator's 200,000 monthly credits cover about 400,000 characters. **Which languages can a cloned voice speak?** Record the sample in any of 23 languages; the cloned voice can then speak 200+ languages. **What happens when I reach my custom-voice limit?** New clones are refused until you free a slot; voices you already have are never deleted or hidden. Deleting a clone frees its slot straight away. The limit is 3 on Basic and unlimited on Creator and above. **Can I clone a celebrity or someone else's voice?** You may only clone a voice you have the right to use — your own, or someone else's with their explicit, informed permission. Nothing about the upload can verify whose voice it is, so this is entirely on you. **Can I clone a voice through the API or an AI agent?** Yes. The REST API exposes POST /api/v1/voice/voice-clone, and the AudioPod MCP server has a clone_voice tool for AI agents and coding assistants, with the same consent rule. ## Related - [Cloning a voice (guide)](https://audiopod.ai/guides/voice/cloning-a-voice) — Step-by-step lesson: recording a good sample, slots and consent. - [Text to Speech](https://audiopod.ai/features/text-to-speech) — Direct a cloned or catalogue voice with emotion, pauses and pronunciation. - [Voice Changer](https://audiopod.ai/features/voice-changer) — Turn a recording into your cloned voice, keeping the timing. - [Voice consent policy](https://audiopod.ai/voice-consent) — How AudioPod handles consent and takedown requests. - [AudioPod vs ElevenLabs](https://audiopod.ai/compare/audiopod-vs-elevenlabs) — Side-by-side comparison, including voice cloning. ## Pricing Plan prices: [pricing](https://audiopod.ai/pricing). Start: [Clone a voice free](https://audiopod.ai/auth/signup?callbackUrl=%2Fdashboard%2Ftools%2Fvoices).