Learn how to replace a pre-existing identity in audio file using the Voice Harbor’s Python SDK, while preserving Emotion and Phonetic information.
We have released our biometric redaction service, read more about all redaction parameters here Job Parameters. Just ask, and we’ll gladly provide more information on why biometric redaction is the recommended approach to comply 100% with HIPAA and GDPR.
Set Up the Client and Create a Job Once you have the necessary setup, you can create a job on the server and interact with the API. Here’s how to do it:
Next, initialize the client and define the parameters for your job, including the files you want to submit for transcription.
Now, submit the job and wait for the transcription results. Here’s how to complete the process:
We are excited to share the release of our revolutionary voice anonymization system for the 2025-05-01, a breakthrough in privacy-preserving speech technology that sets a new standard in both privacy and performance.
Model | EER | UAR | WER |
---|---|---|---|
B1 | 10 | 42 | 2.9 |
B2 | 13 | 55 | 10 |
B5 | 36 | 38 | 4.4 |
B6 | 25 | 36 | 9.1 |
SHIVA Orange | 41 | 41 | 7.8 |
South Korea | 44 | 28 | 5.0 |
FreeVC | 35 | 44 | 4.5 |
NTU-NPU | 42 | 40 | 4.5 |
Voice Harbor V3.0 | 44 | 40 | 3.8 |
Building on the solid foundation of our previous versions, Voice Harbor V3.0 sets a new benchmark in the industry by combining enhanced speech quality, comprehensive multilingual support, and state-of-the-art privacy and utility performance. This release represents a significant leap forward in ensuring secure, high-fidelity speech data transformation for a broad range of applications—from voice bot assistance to academic research.
Voice Harbor V2.0 introduces a cutting-edge approach to secure speech data transformation, prioritizing privacy and compliance. This version features advanced biometric identity redaction, ensuring sensitive audio content is anonymized while maintaining clarity and usability. Fully approved by CNIL, V2.0 upholds the highest standards for data protection, making it an ideal solution for a wide range of applications requiring secure voice processing.