.gitignore
.pre-commit-config.yaml
LICENSE
MANIFEST.in
Package.resolved
Package.swift
README.md
XCODE_BUILD_TROUBLESHOOTING.md
pyproject.toml
pytest.ini
.github/FUNDING.yml
.github/pull_request_template.md
.github/workflows/python-publish.yml
.github/workflows/swift.yml
.github/workflows/tests.yml
.swiftpm/xcode/package.xcworkspace/contents.xcworkspacedata
examples/bible-audiobook/.gitignore
examples/bible-audiobook/README.md
examples/bible-audiobook/bun.lock
examples/bible-audiobook/package.json
examples/bible-audiobook/tsconfig.json
examples/bible-audiobook/audios/bible-akjv/af_heart/00000001-Genesis-1:1.wav
examples/bible-audiobook/audios/bible-akjv/af_heart/00000002-Genesis-1:2.wav
examples/bible-audiobook/audios/bible-akjv/af_heart/00000003-Genesis-1:3.wav
examples/bible-audiobook/audios/bible-akjv/am_michael/00000004-Genesis-1:4.wav
examples/bible-audiobook/audios/bible-akjv/am_michael/00000005-Genesis-1:5.wav
examples/bible-audiobook/audios/bible-akjv/am_michael/00000006-Genesis-1:6.wav
examples/bible-audiobook/bibles/bible-akjv.txt
examples/bible-audiobook/src/convert-to-mp3.ts
examples/bible-audiobook/src/index.ts
examples/bible-audiobook/src/mp3-checker.ts
mlx_audio/__init__.py
mlx_audio/dsp.py
mlx_audio/server.py
mlx_audio/utils.py
mlx_audio/version.py
mlx_audio.egg-info/PKG-INFO
mlx_audio.egg-info/SOURCES.txt
mlx_audio.egg-info/dependency_links.txt
mlx_audio.egg-info/entry_points.txt
mlx_audio.egg-info/requires.txt
mlx_audio.egg-info/top_level.txt
mlx_audio/codec/__init__.py
mlx_audio/codec/models/__init__.py
mlx_audio/codec/models/bigvgan/__init__.py
mlx_audio/codec/models/bigvgan/activation.py
mlx_audio/codec/models/bigvgan/amp.py
mlx_audio/codec/models/bigvgan/bigvgan.py
mlx_audio/codec/models/bigvgan/conv.py
mlx_audio/codec/models/bigvgan/resample.py
mlx_audio/codec/models/descript/__init__.py
mlx_audio/codec/models/descript/base.py
mlx_audio/codec/models/descript/dac.py
mlx_audio/codec/models/descript/nn/__init__.py
mlx_audio/codec/models/descript/nn/layers.py
mlx_audio/codec/models/descript/nn/quantize.py
mlx_audio/codec/models/encodec/__init__.py
mlx_audio/codec/models/encodec/encodec.py
mlx_audio/codec/models/mimi/__init__.py
mlx_audio/codec/models/mimi/mimi.py
mlx_audio/codec/models/mimi/modules/__init__.py
mlx_audio/codec/models/mimi/modules/conv.py
mlx_audio/codec/models/mimi/modules/kv_cache.py
mlx_audio/codec/models/mimi/modules/quantization.py
mlx_audio/codec/models/mimi/modules/seanet.py
mlx_audio/codec/models/mimi/modules/transformer.py
mlx_audio/codec/models/s3/__init__.py
mlx_audio/codec/models/s3/model.py
mlx_audio/codec/models/s3/model_v2.py
mlx_audio/codec/models/s3/utils.py
mlx_audio/codec/models/snac/__init__.py
mlx_audio/codec/models/snac/attention.py
mlx_audio/codec/models/snac/layers.py
mlx_audio/codec/models/snac/snac.py
mlx_audio/codec/models/snac/vq.py
mlx_audio/codec/models/vocos/__init__.py
mlx_audio/codec/models/vocos/mel.py
mlx_audio/codec/models/vocos/vocos.py
mlx_audio/codec/tests/__init__.py
mlx_audio/codec/tests/test_bigvgan.py
mlx_audio/codec/tests/test_descript.py
mlx_audio/codec/tests/test_encodec.py
mlx_audio/codec/tests/test_mimi.py
mlx_audio/codec/tests/test_s3.py
mlx_audio/codec/tests/test_snac.py
mlx_audio/codec/tests/test_vocos.py
mlx_audio/sts/__init__.py
mlx_audio/sts/voice_pipeline.py
mlx_audio/sts/tests/test_voice_pipeline.py
mlx_audio/stt/__init__.py
mlx_audio/stt/generate.py
mlx_audio/stt/utils.py
mlx_audio/stt/models/__init__.py
mlx_audio/stt/models/parakeet/__init__.py
mlx_audio/stt/models/parakeet/alignment.py
mlx_audio/stt/models/parakeet/attention.py
mlx_audio/stt/models/parakeet/audio.py
mlx_audio/stt/models/parakeet/conformer.py
mlx_audio/stt/models/parakeet/ctc.py
mlx_audio/stt/models/parakeet/parakeet.py
mlx_audio/stt/models/parakeet/rnnt.py
mlx_audio/stt/models/parakeet/tokenizer.py
mlx_audio/stt/models/voxtral/__init__.py
mlx_audio/stt/models/voxtral/config.py
mlx_audio/stt/models/voxtral/voxtral.py
mlx_audio/stt/models/wav2vec/__init__
mlx_audio/stt/models/wav2vec/feature_extractor.py
mlx_audio/stt/models/wav2vec/wav2vec.py
mlx_audio/stt/models/whisper/__init__.py
mlx_audio/stt/models/whisper/audio.py
mlx_audio/stt/models/whisper/decoding.py
mlx_audio/stt/models/whisper/timing.py
mlx_audio/stt/models/whisper/tokenizer.py
mlx_audio/stt/models/whisper/whisper.py
mlx_audio/stt/models/whisper/writers.py
mlx_audio/stt/models/whisper/assets/gpt2.tiktoken
mlx_audio/stt/models/whisper/assets/multilingual.tiktoken
mlx_audio/stt/tests/test_models.py
mlx_audio/tests/__init__.py
mlx_audio/tests/test_dsp.py
mlx_audio/tests/test_lazy_imports.py
mlx_audio/tests/test_optional_deps.py
mlx_audio/tests/test_server.py
mlx_audio/tts/__init__.py
mlx_audio/tts/audio_player.py
mlx_audio/tts/convert.py
mlx_audio/tts/generate.py
mlx_audio/tts/utils.py
mlx_audio/tts/models/__init__.py
mlx_audio/tts/models/base.py
mlx_audio/tts/models/interpolate.py
mlx_audio/tts/models/bark/__init__.py
mlx_audio/tts/models/bark/bark.py
mlx_audio/tts/models/bark/isftnet.py
mlx_audio/tts/models/bark/pipeline.py
mlx_audio/tts/models/chatterbox/__init__.py
mlx_audio/tts/models/chatterbox/chatterbox.py
mlx_audio/tts/models/chatterbox/config.json
mlx_audio/tts/models/chatterbox/config.py
mlx_audio/tts/models/chatterbox/tokenizer.py
mlx_audio/tts/models/chatterbox/s3gen/__init__.py
mlx_audio/tts/models/chatterbox/s3gen/decoder.py
mlx_audio/tts/models/chatterbox/s3gen/f0_predictor.py
mlx_audio/tts/models/chatterbox/s3gen/flow.py
mlx_audio/tts/models/chatterbox/s3gen/flow_matching.py
mlx_audio/tts/models/chatterbox/s3gen/hifigan.py
mlx_audio/tts/models/chatterbox/s3gen/mel.py
mlx_audio/tts/models/chatterbox/s3gen/s3gen.py
mlx_audio/tts/models/chatterbox/s3gen/xvector.py
mlx_audio/tts/models/chatterbox/s3gen/matcha/__init__.py
mlx_audio/tts/models/chatterbox/s3gen/matcha/decoder.py
mlx_audio/tts/models/chatterbox/s3gen/matcha/flow_matching.py
mlx_audio/tts/models/chatterbox/s3gen/matcha/transformer.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/__init__.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/activation.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/attention.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/convolution.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/embedding.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/encoder_layer.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/positionwise_feed_forward.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/subsampling.py
mlx_audio/tts/models/chatterbox/s3gen/transformer/upsample_encoder.py
mlx_audio/tts/models/chatterbox/s3tokenizer/__init__.py
mlx_audio/tts/models/chatterbox/s3tokenizer/utils.py
mlx_audio/tts/models/chatterbox/scripts/convert.py
mlx_audio/tts/models/chatterbox/t3/__init__.py
mlx_audio/tts/models/chatterbox/t3/cond_enc.py
mlx_audio/tts/models/chatterbox/t3/learned_pos_emb.py
mlx_audio/tts/models/chatterbox/t3/perceiver.py
mlx_audio/tts/models/chatterbox/t3/t3.py
mlx_audio/tts/models/chatterbox/voice_encoder/__init__.py
mlx_audio/tts/models/chatterbox/voice_encoder/config.py
mlx_audio/tts/models/chatterbox/voice_encoder/melspec.py
mlx_audio/tts/models/chatterbox/voice_encoder/voice_encoder.py
mlx_audio/tts/models/chatterbox_turbo/__init__.py
mlx_audio/tts/models/chatterbox_turbo/chatterbox_turbo.py
mlx_audio/tts/models/chatterbox_turbo/models/__init__.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/__init__.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/decoder.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/encoder.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/flow_matching.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/hifigan.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/mel.py
mlx_audio/tts/models/chatterbox_turbo/models/s3gen/s3gen.py
mlx_audio/tts/models/chatterbox_turbo/models/s3tokenizer/__init__.py
mlx_audio/tts/models/chatterbox_turbo/models/s3tokenizer/utils.py
mlx_audio/tts/models/chatterbox_turbo/models/t3/__init__.py
mlx_audio/tts/models/chatterbox_turbo/models/t3/cond_enc.py
mlx_audio/tts/models/chatterbox_turbo/models/t3/gpt2.py
mlx_audio/tts/models/chatterbox_turbo/models/t3/t3.py
mlx_audio/tts/models/chatterbox_turbo/models/t3/t3_config.py
mlx_audio/tts/models/chatterbox_turbo/models/voice_encoder/__init__.py
mlx_audio/tts/models/chatterbox_turbo/models/voice_encoder/config.py
mlx_audio/tts/models/chatterbox_turbo/models/voice_encoder/melspec.py
mlx_audio/tts/models/chatterbox_turbo/models/voice_encoder/voice_encoder.py
mlx_audio/tts/models/dia/__init__.py
mlx_audio/tts/models/dia/audio.py
mlx_audio/tts/models/dia/config.py
mlx_audio/tts/models/dia/dia.py
mlx_audio/tts/models/dia/layers.py
mlx_audio/tts/models/indextts/__init__.py
mlx_audio/tts/models/indextts/attention.py
mlx_audio/tts/models/indextts/bigvgan.py
mlx_audio/tts/models/indextts/conformer.py
mlx_audio/tts/models/indextts/gpt2.py
mlx_audio/tts/models/indextts/indextts.py
mlx_audio/tts/models/indextts/mel.py
mlx_audio/tts/models/indextts/normalize.py
mlx_audio/tts/models/indextts/perceiver.py
mlx_audio/tts/models/indextts/ecapa_tdnn/__init__.py
mlx_audio/tts/models/indextts/ecapa_tdnn/asp.py
mlx_audio/tts/models/indextts/ecapa_tdnn/ecapa_tdnn.py
mlx_audio/tts/models/indextts/ecapa_tdnn/se_res2net.py
mlx_audio/tts/models/indextts/ecapa_tdnn/tdnn.py
mlx_audio/tts/models/kokoro/__init__.py
mlx_audio/tts/models/kokoro/istftnet.py
mlx_audio/tts/models/kokoro/kokoro.py
mlx_audio/tts/models/kokoro/modules.py
mlx_audio/tts/models/kokoro/pipeline.py
mlx_audio/tts/models/kokoro/voice.py
mlx_audio/tts/models/llama/__init__.py
mlx_audio/tts/models/llama/llama.py
mlx_audio/tts/models/outetts/__init__.py
mlx_audio/tts/models/outetts/audio_processor.py
mlx_audio/tts/models/outetts/dac_interface.py
mlx_audio/tts/models/outetts/default_speaker.json
mlx_audio/tts/models/outetts/outetts.py
mlx_audio/tts/models/outetts/prompt_processor.py
mlx_audio/tts/models/outetts/tokens.py
mlx_audio/tts/models/sesame/__init__.py
mlx_audio/tts/models/sesame/attention.py
mlx_audio/tts/models/sesame/sesame.py
mlx_audio/tts/models/sesame/watermarking.py
mlx_audio/tts/models/spark/__init__.py
mlx_audio/tts/models/spark/audio_tokenizer.py
mlx_audio/tts/models/spark/bicodec.py
mlx_audio/tts/models/spark/spark.py
mlx_audio/tts/models/spark/modules/__init__.py
mlx_audio/tts/models/spark/modules/finite_scalar_quantization.py
mlx_audio/tts/models/spark/modules/residual.py
mlx_audio/tts/models/spark/modules/residual_fsq.py
mlx_audio/tts/models/spark/modules/blocks/__init__.py
mlx_audio/tts/models/spark/modules/blocks/sampler.py
mlx_audio/tts/models/spark/modules/encoder_decoder/__init__.py
mlx_audio/tts/models/spark/modules/encoder_decoder/feat_decoder.py
mlx_audio/tts/models/spark/modules/encoder_decoder/feat_encoder.py
mlx_audio/tts/models/spark/modules/encoder_decoder/wave_generator.py
mlx_audio/tts/models/spark/modules/speaker/__init__.py
mlx_audio/tts/models/spark/modules/speaker/ecapa_tdnn.py
mlx_audio/tts/models/spark/modules/speaker/perceiver_encoder.py
mlx_audio/tts/models/spark/modules/speaker/pooling_layers.py
mlx_audio/tts/models/spark/modules/speaker/speaker_encoder.py
mlx_audio/tts/models/spark/utils/audio.py
mlx_audio/tts/models/spark/utils/file.py
mlx_audio/tts/models/spark/utils/token_parser.py
mlx_audio/tts/models/vibevoice/__init__.py
mlx_audio/tts/models/vibevoice/acoustic_tokenizer.py
mlx_audio/tts/models/vibevoice/config.py
mlx_audio/tts/models/vibevoice/diffusion_head.py
mlx_audio/tts/models/vibevoice/language_model.py
mlx_audio/tts/models/vibevoice/scheduler.py
mlx_audio/tts/models/vibevoice/vibevoice.py
mlx_audio/tts/models/voxcpm/__init__.py
mlx_audio/tts/models/voxcpm/audio_vae.py
mlx_audio/tts/models/voxcpm/config.py
mlx_audio/tts/models/voxcpm/dit.py
mlx_audio/tts/models/voxcpm/encoder.py
mlx_audio/tts/models/voxcpm/minicpm.py
mlx_audio/tts/models/voxcpm/voxcpm.py
mlx_audio/tts/tests/__init__.py
mlx_audio/tts/tests/test_base.py
mlx_audio/tts/tests/test_convert.py
mlx_audio/tts/tests/test_interpolate.py
mlx_audio/tts/tests/test_models.py
mlx_audio/tts/tests/test_voxcpm.py
mlx_audio/tts/tests/test_voxcpm_integration.py
mlx_audio/ui/.eslintrc.json
mlx_audio/ui/.gitignore
mlx_audio/ui/README.md
mlx_audio/ui/components.json
mlx_audio/ui/next.config.mjs
mlx_audio/ui/package.json
mlx_audio/ui/postcss.config.mjs
mlx_audio/ui/tailwind.config.ts
mlx_audio/ui/tsconfig.json
mlx_audio/ui/app/favicon.ico
mlx_audio/ui/app/globals.css
mlx_audio/ui/app/layout.tsx
mlx_audio/ui/app/page.tsx
mlx_audio/ui/app/fonts/GeistMonoVF.woff
mlx_audio/ui/app/fonts/GeistVF.woff
mlx_audio/ui/app/speech-to-text/page.tsx
mlx_audio/ui/app/speech-to-text/[id]/page.tsx
mlx_audio/ui/app/speech-to-text/realtime/page.tsx
mlx_audio/ui/app/text-to-speech/page.tsx
mlx_audio/ui/components/audio-orb.tsx
mlx_audio/ui/components/footer.tsx
mlx_audio/ui/components/layout-wrapper.tsx
mlx_audio/ui/components/navbar.tsx
mlx_audio/ui/components/sidebar.tsx
mlx_audio/ui/components/theme-provider.tsx
mlx_audio/ui/components/theme-toggle.tsx
mlx_audio/ui/components/voice-library.tsx
mlx_audio/ui/components/voice-selection.tsx