A free speech to speech tool that changes the voice of any recording and keeps its words, timing and emotion, in your browser.
5.0(1 rating)Made a video with an AI tool, in a voice that isn't yours? Put it in your own voice, or any other, and keep every word and the timing. It runs in this browser, and nothing is uploaded.
Your video or recording
The new voice
Change the voice
Hear it and save it
Your file in the new voice shows here, to hear before you save it.
Your file and your voice never leave this browser. The models download from our server once, and nothing you add is uploaded.
Speech to speech changes the voice in a recording and keeps what was said and how it was said. This free speech to speech tool does it in your browser, into your own voice or a ready-made one.
Text to speech starts from words you type. Speech to speech starts from someone talking, so the timing and the feeling come from a real recording.
Nothing is uploaded: the recording and your voice stay on your computer.
What is speech to speech?
Speech to speech takes a recording of someone talking and gives it a different voice. The words, the pauses and the emotion stay; only the voice changes.
ElevenLabs used to call its version Speech to Speech, and calls it Voice Changer now. It's the same idea.
Speech to speech vs text to speech
They both end with a voice saying something, but they start from different places. This table sets them side by side.
- Speech to speech
- A recording of someone talking
- Text to speech
- Text you type
- Speech to speech
- The words, the timing and the delivery
- Text to speech
- Nothing but the text
- Speech to speech
- A real person did the performance
- Text to speech
- The model makes up the delivery
- Speech to speech
- This tool
- Text to speech
- Text to speech, or voice cloning for your own voice
How speech to speech works
This tool does it in 4 steps, all in your browser.
- It finds the voice – a model takes the voice off the music and background.
- It turns the voice into speech codes – numbers that carry the words and the timing, but not whose voice it is.
- It says those codes in the new voice – a voice model reads up to 20 seconds of the new voice and renders the codes in it.
- It puts it back – over the untouched background, as long as the original to within a fraction of a second.
That's the Keep the delivery mode. The tool's default, Best likeness, writes down each line and says it in the new voice instead, which sounds more like the new voice.
How to use speech to speech
These are the steps, from a recording to the new voice.
What I measured
I ran speech to speech on my own voice and a woman's. A speaker recognition model scored each result from -1 to 1 against the new voice.
- Words
- Every word right
- Sounds like the new voice
- 0.52 (my own voice: 0.30)
- Words
- Kept
- Sounds like the new voice
- 0.35
- Words
- Kept
- Sounds like the new voice
- 0.42 (their own voice: 0.17)
A woman's voice from a clean sample came through clearly, with every word right. My own voice got closer with a longer sample of me.
Who is speech to speech for?
It's for anyone with a good performance in the wrong voice.
- AI voice changer – everything the voice changer does, with both modes
- Voice cloning – creators who want new lines in their own voice
- Speech to text – anyone who needs the words written down too
- Remove music from video – editors who want the voice on its own
Change your own voice, or one you have permission for, and say it's AI when you publish it.
Want a pro voice?
The best pro voice
Speech to speech FAQs
Questions about the speech to speech? Here's what to know.
Speech to speech takes a recording of someone talking and gives it a different voice.
The words, the pauses and the emotion stay the same.
Text to speech starts from words you type, and the model makes up the delivery.
Speech to speech starts from a real recording, so the timing and the feeling are a person's.
Yes, in Keep the delivery mode: the timing and the emotion come from the original recording.
Best likeness says each line fresh in the new voice, and sounds more like it.
Yes: click Add your voice, then record, upload or paste a link.
A voice from a link has to match you: you read one sentence, and it checks.
No, your recording and your voice stay in your browser.
Only the models download, once, from our server.
Yes, it's free, with no account and no watermark.
I did.
I'm Navid Moazzez, and the speech to speech tool is one of my free tools on navid.me.
Read more about me.
Navid Moazzez
AI business strategist & AI OS builder
Navid Moazzez helps creators and founders master AI and build their own AI Operating System (AI OS) to automate their business and life.
Navid.me is reader-supported. When you buy through links on this site, I may earn an affiliate commission. Learn more.
More free tools
TikTok
Instagram
X
Bluesky
LinkedIn
Threads
Mastodon
Pinterest
YouTube
Amazon KDP
Apple Books
Amazon
Substack
Spotify
Apple Podcasts
Free AI newsletterThe most actionable AI newsletter for founders
Every week, get proven AI strategies, curated tools, and step-by-step systems to grow your audience, create better content, and build a profitable creator business.
No fluff, no filler, no BS. Just five minutes each week that might level up your online business and life.
P.S. Sign up now to get free access to my ultimate AI tools guide for creators.
