Audio Isolation

Use AI to extract clean vocals or speech from noisy audio.

This is useful for podcast cleanup, speech recognition preprocessing, or removing background noise in recorded clips. Powered by ElevenLabs Audio Isolation API.

---

✅ Basic Usage

AudioClip rawRecording = Resources.Load<AudioClip>("NoisyInput");

AudioClip cleanSpeech = await rawRecording
    .GENAudioIsolation()
    .SetOutputFormat(OutputFormat.MPEG)
    .ExecuteAsync();

🧼 The resulting clip will contain mostly vocal content, with noise removed or reduced.

---

⚙️ Configuration Options

Method	Description
SetOutputFormat(format)	Choose output format (MP3, WAV, PCM, etc.)
SetOutputPath(path)	Save location for processed file

---

📦 Example Use Case

Input: Phone recording with background street noise Output: Voice is isolated and easier to transcribe or play back cleanly

---

🧠 Tips

• Pair this with Speech to Text to dramatically improve transcription accuracy.

• If used in real-time input pipelines, consider pre-buffering audio and applying .AsAudioClip() conversion before playback.