Mix audio tracks
Layer voices and music into one file, with the music dipping under speech.
By their sound, when each person recorded their own.
It comes back up in the pauses.
More options
From a little to a lot.
Free for the first 3 minutes, 3 times a day. No sign-up.
One after another instead? Join audio
Hear the difference
Play Layered, then Mixed.
Speaker 1, Speaker 2, Music. Mixed: the music dips under the voices 2 times.
Both made with Mix tracks · Mixed lowers the music under voices
Voices in these examples are AI-generated.
Works in any language
- Hello
- こんにちは
- Hola
- 안녕하세요
- Bonjour
- नमस्ते
- Hallo
- 你好
- Ciao
- مرحبا
- Olá
- Привет
- Hoi
- สวัสดี
- Merhaba
- Γεια σας
- Xin chào
- שלום
- வணக்கம்
- Kia ora
How to mix audio tracks
- 1
Add 2 to 20 tracks, such as voices and music.
- 2
Mark the music, and set each track's volume and start.
- 3
Download one mixed file.
Questions
Is it free?
Yes, for the first 3 minutes of the mix, 3 times a day, with no sign-up. For longer files, see pricing.
What does lowering the music do?
While anyone speaks, the music dips well under the voices, then comes back up in the pauses, as on the radio.
What does lining up do?
When each person records their own track, the files rarely start at the same moment, and they drift apart. Audo lines them up by their sound and keeps them in step to the end.
How is it different from Join audio?
Join plays files one after another. Mix plays them at the same time, layered.
More tools
- Cut audioTrim start, middle or end.
- Join audioMerge files into one.
- Remove silenceCut out long pauses.
- Remove noiseMake noisy recordings clear.
- Remove echoMake voices sound close.
- Audio enhancerStudio sound for any voice.
- Transcribe audioSpeech to text, who said what.
- Script to captionsSync a script to audio.
- Remove filler wordsCut the ums and uhs.
- Boost volumeMake quiet audio louder.
For AI assistants and developers
Ask ChatGPT, Claude, or a coding agent to do this for you, or call it from your own code.
Show the free API call
curl -F file=@voice.wav -F file=@music.mp3 -F 'tracks=[{"role":"voice"},{"role":"music","volume_db":-6}]' -F duck=true https://audo.ai/api/try/mix -o voice-mix.wav