resemble-ai/Resemblyzer

Health v2 · maintenance only

Adoption not part of the score

3300 stars · 479 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Resemblyzer is a Python package that uses a deep learning voice encoder to convert speech audio into 256-dimensional voice embeddings. These embeddings enable voice comparison, speaker verification, diarization, and fake speech detection.

Use cases

• compare how similar two voices sound
• verify a speaker's identity from a few seconds of reference audio
• diarize a multi-speaker recording to see who is talking when
• detect deepfake or fake speech
• extract voice embeddings for downstream ML models
• cluster utterances by speaker

When to choose

• you need speaker embeddings or voice similarity in Python with minimal setup
• you want speaker diarization or verification without training a model
• you need a lightweight pretrained voice encoder for research or prototyping

When to avoid

• you need full speech-to-text transcription
• you need production-grade text-to-speech or voice cloning
• you require actively maintained software with recent releases
• you need real-time streaming speaker recognition

Facets

library · maturity maintenance

machine-learning audio-processing speech-recognition nlp machine-learning speech-processing artificial-intelligence python cross-platform voice-encoder speaker-verification speaker-diarization voice-embeddings deep-learning audio-embeddings audio

Member repositories

For agents

markdown · JSON · MCP: product_card(name="resemble-ai/Resemblyzer")