# AI voice changer: change your voice online in audio and video

Record your voice or upload a clip, and swap it into a realistic male or female speech-to-speech voice while keeping your exact timing, pauses, and laughs.

## How it works

1. Record your voice in the browser, or drop an audio or video file up to 10 GB.
2. Preview and choose a male or female voice and model—Eleven Multilingual STS v2 or HeyGen Voice STS.
3. Convert your recording, compare it side by side with the original, and download.

## Your performance, spoken in a realistic new voice

Audo's online voice changer and speech-to-speech voice changer transforms the speaker's voice in WAV, MP3, M4A, FLAC, OGG, MP4, MOV, MKV, WebM, and AVI files up to 10 GB—or straight from your browser microphone and webcam—using Eleven Multilingual STS v2 (29 languages) and HeyGen Voice STS (39 languages). The first 30 seconds of any clip are free, 3 times a day with no sign-up, and recordings over four minutes are split automatically inside natural pauses and joined seamlessly at -16 LUFS.

Unlike a simple pitch shifter that stretches frequencies higher or lower and leaves speech sounding hollow, Audo's AI voice changer replaces vocal timbre and resonance while preserving every pause, whisper, sigh, laugh, and emphasis from your original performance. Use it as a realistic female to male voice changer, male to female voice changer, deep voice changer for narration, or video voice changer that anonymizes an interview source while keeping the video picture untouched.

Preview all 20 male and female voices at matched loudness before running a file, compare the original and converted takes side by side on one timeline, or open the result in Audo's editor to layer background music with Mix audio and burn subtitles with Auto captions. Developers and AI assistants can run the same change_voice tool through Audo's REST API and MCP server.

Tool: Voice changer (`change_voice`). Price: 30 credits a minute — $0.30/min ($18.00/hr), pay-as-you-go with no monthly subscription — of input for whole files, charged only when a job succeeds.

## Free API

```bash
curl -F file=@recording.mp3 -F model=eleven_sts_v2 -F voice=george https://audo.ai/api/try/voice-changer -D response.headers -o response.body
```

Read response.headers and response.body before naming media. Handle 202, 200 JSON and errors with the complete response client at https://audo.ai/docs/api?utm_source=markdown&utm_medium=agent#responses.

Free for the first 30 seconds of each file, 3 times a day per person, with no key or account. Uploads up to 10 GB, 2 at once from one address. The response is the result itself; a job that runs longer than about 30 seconds returns 202 with a link to check on it. With an API key (`-H "Authorization: Bearer $AUDO_API_KEY"`), omitting free runs the whole file with credits if the balance covers it, otherwise the free portion if quota remains. Set free=true to prohibit spending; for paid whole files use free=false with an approved positive max_credits. A free result cut short comes with finishUrl (and the Audo-Finish-Url header when the response is the file itself): give it to the person, who pays there (from $5, no sign-up), and the whole file runs; keep checking the status link, whose finishedBy names the whole-file job and its own status link. Details: https://audo.ai/docs/api.md

## Options

Form fields with the same names as the MCP tool's inputs:

- `model`: The speech-to-speech model and its price a minute: eleven_sts_v2 (Eleven Multilingual STS v2, 30 credits), heygen_sts (HeyGen Voice STS, 30 credits). Default eleven_sts_v2.
- `voice`: The model's target voice. Eleven (george, sarah, brian, alice, daniel, lily, adam, matilda; default george). HeyGen (annie, lewis, joanna, wade, leanne, roderic, janet, brodie, prudence, garret, tori, gordon; default annie).
- `remove_background_noise`: Removes background noise from the recording before changing the voice. Default true.
- `auto_volume`: Sets the whole file to -16 LUFS with one gain, and limits peaks to -1 dBTP. It doesn't balance loud and quiet speakers. Default true.
- `output_format`: The result's format: same (as the input; a video stays a video), wav, mp3, m4a, or flac. Default same.

## Languages

Any language: it works on the sound, not the words.

## From an assistant (MCP)

Add https://audo.ai/mcp and sign in (setup for each assistant: https://audo.ai/setup.md). The tool is `change_voice`:

> Changes the speaker's voice in an audio or video recording while keeping their exact words, timing, pauses, whispers, and laughs. Works on video: the picture is copied untouched when output_format is same. Choose model (eleven_sts_v2, heygen_sts, default eleven_sts_v2) and one of its voices; remove_background_noise cleans noisy takes first. Not for reading a text script (text_to_speech) or restoring a speaker's own voice (enhance_voice). It costs 30 credits a minute, charged only if the job succeeds. Returns download links, or job_id for get_job.

Example: "Change the voice in this video to George with Eleven Multilingual STS v2."

## Questions

**Is there a free online AI voice changer with no download?** Yes. Audo runs directly in your browser with no install and converts the first 30 seconds of any audio or video recording free, 3 times a day, with no sign-up. Whole recordings cost $0.30 a minute ($18.00 an hour), shown before anything runs and charged only if it succeeds, with no subscription.

**Can I change a female voice to male, or male to female, realistically?** Yes. Standard pitch changers shift formants up or down and sound artificial past a few semitones, whereas Audo's neural speech-to-speech models rebuild vocal resonance into real male voices (such as George, Brian, or Wade) and female voices (such as Sarah, Alice, or Annie) while keeping your exact cadence and phrasing. If you only want to transpose a song or shift semitones without swapping the speaker, use Change pitch.

**How do I change my voice in a video, or record my voice directly online?** Press Record on Audo's voice changer page to capture your microphone or webcam directly in the browser, or drop an MP4, MOV, MKV, WebM, or AVI file up to 10 GB. For videos, Audo swaps the voice track while copying the video stream directly, so the picture loses zero quality and lip movements stay aligned with every word.

**How is speech-to-speech different from text to speech, and does it work in real time?** Text to speech generates pacing from written words, so you cannot act out exact pauses, whispers, or laughs. Audo's speech-to-speech voice changer converts a recorded take so every syllable and breath lands on the exact same moment as your performance. Because Audo processes recordings and videos up to 10 GB rather than live microphone loopback, it is built for videos, podcasts, voiceovers, and interviews rather than live gaming chat.

**Should I pick Eleven Multilingual STS v2 or HeyGen Voice STS?** On Audo, Eleven Multilingual STS v2 supports 29 languages and excels at subtle vocal nuances such as whispers, sighs, laughs, and regional accents. HeyGen Voice STS supports 39 languages and runs HeyGen's voice engine, ranked first on Artificial Analysis' blind voice similarity benchmark. Both work on long recordings without a 5-minute file cap.

**What if my recording has background noise or music?** Voice conversion works best on single-speaker speech without music. Remove background noise is on by default in Audo's voice changer to clean up mic hiss and room noise before converting; for heavy noise you can also run Remove noise first, and for music behind speech, separate the voice first with Vocal remover.

## More

- Every tool: https://audo.ai/llms.txt
- OpenAPI: https://audo.ai/api/openapi.json
- This page for people: https://audo.ai/voice-changer?utm_source=markdown&utm_medium=agent