├── .env.template ├── .gitattributes ├── .gitignore ├── LICENSE ├── README.md ├── assets ├── system_architecture.svg ├── timing_chart.png └── video_demo.mov ├── data ├── models │ └── kokoro.pth └── voices │ ├── af.pt │ ├── af_alloy.pt │ ├── af_aoede.pt │ ├── af_bella.pt │ ├── af_bella_nicole.pt │ ├── af_heart.pt │ ├── af_jessica.pt │ ├── af_kore.pt │ ├── af_nicole.pt │ ├── af_nicole_sky.pt │ ├── af_nova.pt │ ├── af_river.pt │ ├── af_sarah.pt │ ├── af_sarah_nicole.pt │ ├── af_sky.pt │ ├── af_sky_adam.pt │ ├── af_sky_emma.pt │ ├── af_sky_emma_isabella.pt │ ├── am_adam.pt │ ├── am_michael.pt │ ├── bf_alice.pt │ ├── bf_emma.pt │ ├── bf_isabella.pt │ ├── bm_george.pt │ ├── bm_lewis.pt │ ├── ef_dora.pt │ ├── if_sara.pt │ ├── jf_alpha.pt │ ├── jf_gongitsune.pt │ ├── pf_dora.pt │ ├── zf_xiaoxiao.pt │ └── zf_xiaoyi.pt ├── requirements.txt ├── speech_to_speech.py ├── src ├── config │ └── config.json ├── core │ └── kokoro.py ├── models │ ├── istftnet.py │ ├── models.py │ └── plbert.py └── utils │ ├── __init__.py │ ├── audio.py │ ├── audio_io.py │ ├── audio_queue.py │ ├── audio_utils.py │ ├── commands.py │ ├── config.py │ ├── generator.py │ ├── llm.py │ ├── speech.py │ ├── text_chunker.py │ └── voice.py └── text_to_speech.py /.env.template: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/.env.template -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/.gitattributes -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/README.md -------------------------------------------------------------------------------- /assets/system_architecture.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/assets/system_architecture.svg -------------------------------------------------------------------------------- /assets/timing_chart.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/assets/timing_chart.png -------------------------------------------------------------------------------- /assets/video_demo.mov: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/assets/video_demo.mov -------------------------------------------------------------------------------- /data/models/kokoro.pth: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/models/kokoro.pth -------------------------------------------------------------------------------- /data/voices/af.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af.pt -------------------------------------------------------------------------------- /data/voices/af_alloy.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_alloy.pt -------------------------------------------------------------------------------- /data/voices/af_aoede.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_aoede.pt -------------------------------------------------------------------------------- /data/voices/af_bella.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_bella.pt -------------------------------------------------------------------------------- /data/voices/af_bella_nicole.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_bella_nicole.pt -------------------------------------------------------------------------------- /data/voices/af_heart.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_heart.pt -------------------------------------------------------------------------------- /data/voices/af_jessica.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_jessica.pt -------------------------------------------------------------------------------- /data/voices/af_kore.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_kore.pt -------------------------------------------------------------------------------- /data/voices/af_nicole.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_nicole.pt -------------------------------------------------------------------------------- /data/voices/af_nicole_sky.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_nicole_sky.pt -------------------------------------------------------------------------------- /data/voices/af_nova.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_nova.pt -------------------------------------------------------------------------------- /data/voices/af_river.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_river.pt -------------------------------------------------------------------------------- /data/voices/af_sarah.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_sarah.pt -------------------------------------------------------------------------------- /data/voices/af_sarah_nicole.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_sarah_nicole.pt -------------------------------------------------------------------------------- /data/voices/af_sky.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_sky.pt -------------------------------------------------------------------------------- /data/voices/af_sky_adam.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_sky_adam.pt -------------------------------------------------------------------------------- /data/voices/af_sky_emma.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_sky_emma.pt -------------------------------------------------------------------------------- /data/voices/af_sky_emma_isabella.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/af_sky_emma_isabella.pt -------------------------------------------------------------------------------- /data/voices/am_adam.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/am_adam.pt -------------------------------------------------------------------------------- /data/voices/am_michael.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/am_michael.pt -------------------------------------------------------------------------------- /data/voices/bf_alice.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/bf_alice.pt -------------------------------------------------------------------------------- /data/voices/bf_emma.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/bf_emma.pt -------------------------------------------------------------------------------- /data/voices/bf_isabella.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/bf_isabella.pt -------------------------------------------------------------------------------- /data/voices/bm_george.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/bm_george.pt -------------------------------------------------------------------------------- /data/voices/bm_lewis.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/bm_lewis.pt -------------------------------------------------------------------------------- /data/voices/ef_dora.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/ef_dora.pt -------------------------------------------------------------------------------- /data/voices/if_sara.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/if_sara.pt -------------------------------------------------------------------------------- /data/voices/jf_alpha.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/jf_alpha.pt -------------------------------------------------------------------------------- /data/voices/jf_gongitsune.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/jf_gongitsune.pt -------------------------------------------------------------------------------- /data/voices/pf_dora.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/pf_dora.pt -------------------------------------------------------------------------------- /data/voices/zf_xiaoxiao.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/zf_xiaoxiao.pt -------------------------------------------------------------------------------- /data/voices/zf_xiaoyi.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/data/voices/zf_xiaoyi.pt -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/requirements.txt -------------------------------------------------------------------------------- /speech_to_speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/speech_to_speech.py -------------------------------------------------------------------------------- /src/config/config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/config/config.json -------------------------------------------------------------------------------- /src/core/kokoro.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/core/kokoro.py -------------------------------------------------------------------------------- /src/models/istftnet.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/models/istftnet.py -------------------------------------------------------------------------------- /src/models/models.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/models/models.py -------------------------------------------------------------------------------- /src/models/plbert.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/models/plbert.py -------------------------------------------------------------------------------- /src/utils/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/__init__.py -------------------------------------------------------------------------------- /src/utils/audio.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/audio.py -------------------------------------------------------------------------------- /src/utils/audio_io.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/audio_io.py -------------------------------------------------------------------------------- /src/utils/audio_queue.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/audio_queue.py -------------------------------------------------------------------------------- /src/utils/audio_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/audio_utils.py -------------------------------------------------------------------------------- /src/utils/commands.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/commands.py -------------------------------------------------------------------------------- /src/utils/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/config.py -------------------------------------------------------------------------------- /src/utils/generator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/generator.py -------------------------------------------------------------------------------- /src/utils/llm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/llm.py -------------------------------------------------------------------------------- /src/utils/speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/speech.py -------------------------------------------------------------------------------- /src/utils/text_chunker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/text_chunker.py -------------------------------------------------------------------------------- /src/utils/voice.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/src/utils/voice.py -------------------------------------------------------------------------------- /text_to_speech.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/asiff00/On-Device-Speech-to-Speech-Conversational-AI/HEAD/text_to_speech.py --------------------------------------------------------------------------------