andabi/deep-voice-conversion

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

3938 stars · 824 forks observed · 2026-08-28

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

A TensorFlow implementation of deep neural networks for voice conversion (voice style transfer) that converts a source speaker's voice into a target speaker's voice without parallel training data. It uses a two-module architecture (phoneme classification plus speech synthesis) with CBHG modules from Tacotron.

Use cases

• convert my voice to sound like another speaker
• voice style transfer with deep learning
• train a voice conversion model without parallel data
• clone a target speaker's voice from waveforms
• experiment with Tacotron-style speech synthesis
• phoneme classification from spectrograms

When to choose

• you want to convert speech to a specific target speaker using only target waveforms
• you need a research/educational reference implementation of non-parallel voice conversion
• you work in TensorFlow and want to study CBHG-based speech models

When to avoid

• you need production-quality, real-time voice conversion
• you want a maintained tool with recent updates or pretrained multi-speaker models
• you need a simple API rather than a research codebase requiring TIMIT and custom datasets

Facets

library · maturity maintenance

deep-learning speech-recognition audio-processing machine-learning speech-processing deep-learning machine-learning python voice-conversion tensorflow speech-synthesis style-transfer non-parallel-data audio linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="andabi/deep-voice-conversion")