From a reference · Creator+

Hear your lyrics sung in a voice like your reference vocal

Add 30 seconds or more of a vocal you have the rights to and paste your lyrics. Get a new take with a title and cover art. On the Creator plan and above.

1,000 free tokens to start · No card needed · Cancel paid plans anytime

Unlock Similar Singing Generator with Creator — from $9.99/mo, or ₹399/mo in India. 4,000 tokens a month. Billed $119.88 a year, or $12.49 month to month.

What you get

Demo in the voice you hear

Use a recording of your own voice as the reference and hear new lyrics in a voice like it, before you book a session.

Your words, exactly

Your lyrics are sung as written, up to about the first 350 characters, roughly a verse and a chorus.

A vocal to build on

Download the take, or open it in AI Studio and build an instrumental around it with AI Stem Generator.

Who it's for

Songwriters

Hear a verse and a chorus sung in a voice like yours, or like a consenting singer's, before anyone steps into the booth.

Producers

Demo a topline in a voice like the artist's, from a reference take they sent you with their permission.

Independent artists

Try new lyrics in a voice like your own from one recorded take, without singing every draft yourself.

When to use it

  • You wrote new lyrics and want to hear them in a voice like yours before recording
  • The singer you're writing for has sent a reference take and their OK, but can't record yet
  • You're choosing between two lyric drafts and want to hear each one sung
  • A song idea needs a guide vocal before you build a track around it
  • Your only recording of the voice is inside a full mix

What you can make with it

A guide for the session singer

With the singer's reference and permission, generate a guide so they can hear the new lyric sung before they record.

Voice-memo demos

Sing 30 seconds or more into your phone, upload the take, and use it as the reference for each new lyric idea.

A lyric draft shoot-out

Run two versions of a chorus through the same reference and keep the one that sings better.

A check on a crowded line

Hear whether a line sounds crowded or awkward when it's sung, before you take it to the booth.

A vocal-first song

Take the generated vocal into AI Studio and add drums, bass or a full instrumental under it with AI Stem Generator.

A reference pulled from a mix

If the take you want to use is buried in a song, split it with Stem Separator first and use the vocal stem as the reference.

Two voices, one lyric

Run the same lyrics with your own reference and with a collaborator's, with their OK, to hear which voice suits the song.

Screenshots

The Similar Singing Generator panel with a reference vocal slot and lyrics typed in.
Add a reference vocal and your lyrics to sing them in a similar voice.

Similar Singing Generator sings your lyrics in a voice like a reference vocal you supply. Add at least 30 seconds of the voice and your words, and Agent One delivers a new vocal performance with a title and cover art. It's built for songwriters and producers who want to hear lyrics in a particular voice, including their own, before a full session, and it should only be used with a voice you own or have permission to use.

See it in action

How it works

  1. Add a reference vocal

    Open Similar Singing Generator under Create in AI Tools and add a vocal of at least 30 seconds from your Library or your device.

  2. Add your lyrics

    Write or paste your lyrics, or use Help me write to draft them. Only about the first 350 characters are sung, roughly a verse and a chorus.

  3. Choose a model version

    Pick a model version from the Model / Version menu at the top of the panel. There's no style or prompt field, because the reference sets the voice.

  4. Generate and use the vocal

    Click Generate in Chat. Agent One sings your lyrics in a voice like the reference and delivers the vocal with a title and cover art, ready to play, download or open in AI Studio.

Why use Similar Singing Generator

A voice from a reference

Hear your lyrics in a voice like the one in your reference vocal, without booking a session.

Your words, exactly

Your lyrics are sung as you wrote them, up to about the first 350 characters, roughly a verse and a chorus.

Works with your own voice

Record yourself once and use that take as the reference to hear new lyrics in your own voice.

Ready for the next step

Download the vocal as MP3, or open it in AI Studio and build an instrumental around it with AI Stem Generator.

What it costs

Needs Creator or above, for every version. Soundverse v9 needs Pro.

  • Vocal with Soundverse v6: 300 tokens (about $0.75–$0.94 on Creator, or ₹30–₹37 in India).
  • Vocal with Soundverse v7: 400 tokens (about $1.00–$1.25 on Creator, or ₹40–₹50 in India).
  • Vocal with Soundverse v8: 400 tokens (about $1.00–$1.25 on Creator, or ₹40–₹50 in India).
  • Vocal with Soundverse v9: 500 tokens (about $1.25–$1.56 on Pro, or ₹52–₹65 in India).

Agent One runs this tool for you, and the agent's own steps are metered on top of the tool's price: about 7 tokens a step in Lite mode, 54 in Standard mode and 128 in Pro mode, the default on paid plans.

Creator $12.49 a month, or $9.99 a month billed yearly ($119.88 a year) · Pro $31.24 a month, or $24.99 a month billed yearly ($299.88 a year) · Max from $72 a month, or $60 a month billed yearly ($720 a year).

In India (PayU): Creator ₹499 a month, or ₹399 a month billed yearly (₹4,788 a year) · Pro ₹1,299 a month, or ₹1,039 a month billed yearly (₹12,468 a year) · Max from ₹2,999 a month, or ₹2,399 a month billed yearly (₹28,788 a year).

Prices outside India are in US dollars, billed through Stripe; in India they are in rupees, billed through PayU. Monthly tokens reset each month and don't roll over.

Frequently asked questions

Is Similar Singing Generator free?

No. Similar Singing Generator is part of the Creator plan and above, and each vocal you generate uses tokens; the panel shows the estimate before you start. Soundverse accounts are free to create, and new accounts get starter tokens to try the tools on the Free plan.

What makes a good reference vocal?

Similar Singing Generator needs at least 30 seconds of reference audio, as MP3, WAV, AAC, OGG, M4A or MP4, and the panel won't take a shorter clip. The field asks for a vocal, so a solo vocal take is the intended input. If your reference is a full song, run Stem Separator first to pull out the vocal.

Can I release songs with vocals from Similar Singing Generator?

Paid plans, the only ones that include Similar Singing Generator, add a commercial license; the Pricing page lists what each plan covers. Releasing a vocal also depends on the voice: you need the rights to the reference recording and the singer's permission to use their voice.

What can't Similar Singing Generator do?

Similar Singing Generator has no style or prompt controls: the reference sets the voice and your lyrics set the words. It doesn't write lyrics on its own, though Help me write can draft them, and it needs at least 30 seconds of reference audio. To build a full track around the vocal, AI Stem Generator can create a matching instrumental in AI Studio.

Does Similar Singing Generator clone the singer's voice?

Yes. Similar Singing Generator clones the voice in your reference vocal and sings your lyrics with it, so treat it as voice cloning. Use your own voice or the voice of a singer who has given you explicit permission, and never use it to pass a performance off as a real artist's.

What is Similar Singing Generator?

Similar Singing Generator is a Soundverse tool that sings lyrics you provide in a voice like a reference vocal you supply. It clones the voice from a reference of at least 30 seconds, and Agent One delivers the new vocal performance with a title and cover art.

How do I make AI sing my lyrics in a reference voice?

Open Similar Singing Generator, add a reference vocal of at least 30 seconds from your Library or device, then type or paste your lyrics. Pick a model version and generate, and Similar Singing Generator sings about the first 350 characters of your lyrics, word for word, in a voice like the reference. Only use a voice you own or have permission to use.

How is Similar Singing Generator different from AI Singing Generator?

AI Singing Generator sings your lyrics in a vocal style you pick from a list, such as Pop (Female), and a voice sample is optional. Similar Singing Generator always starts from a reference vocal and sings in a voice like it. To reuse your own voice across many songs, Train Voice Clone saves it as a reusable voice instead.

Ready to hear your lyrics sung?

Add a reference vocal you have the rights to, type your lyrics, and get a new take in a voice like it.

Setting up your studio…Warming up Agent One…Tuning the instruments…Getting your library ready…Almost there…