v0.2.5

What's Changed

• Use indeterminate progress for CSM models by @lucasnewman in #216
• Bump version to 0.2.5 by @Blaizzy in #219

Full Changelog: v0.2.4...v0.2.5

v0.2.4

What's Changed

• move sentence splitting into a separate utility class and add unit tests by @smdesai in #183
• Add BigVGAN neural audio codec by @senstella in #186
• fix: (outetts)loading model: Speaker file not found. by @zysam in #189
• Fix deprecated save in MLX-LM by @Blaizzy in #194
• Implementation of Misaki G2P tokenizer by @smdesai in #193
• Add IndexTTS by @senstella in #187
• Load both lexicon files us_gold and us_silver with words in us_gold taking precedence by @smdesai in #195
• Add S3 semantic tokenizer / neural audio codec by @lucasnewman in #204
• add lexicon files for British sounds, gb_gold and gb_silver by @smdesai in #197
• Fix Mimi codec by @lucasnewman in #209
• Add ability to use a custom URL to load Kokoro safetensors by @adrgrondin in #185
• Handle transformers-style config for Sesame CSM models by @lucasnewman in #211
• Add Xcode build troubleshooting documentation by @kinkadius in #210
• Multi model support by @ivanfioravanti in #213
• Add voxtral by @Blaizzy in #214

New Contributors

• @zysam made their first contribution in #189
• @adrgrondin made their first contribution in #185
• @kinkadius made their first contribution in #210

Full Changelog: v0.2.3...v0.2.4

v0.2.3

What's Changed

• Add custom Voice Cloning OuteTTS by @Blaizzy in #172
• Fix Outetts long generation by @Blaizzy in #174
• Adding streaming support for Kokoro and an iOS target app by @smdesai in #173
• Audio player output buffering for streaming mode by @lucasnewman in #170
• Update Swift Package paths by @rudrankriyam in #179
• Add Orpheus to MLX-Audio-Swift by @BenLumenDigital in #182
• Make KokoroTTSModel properties and methods public for better accessibility by @rudrankriyam in #180
• Add streaming support to OuteTTS by @lucasnewman in #169

New Contributors

• @smdesai made their first contribution in #173
• @rudrankriyam made their first contribution in #179

Full Changelog: v0.2.2...v0.2.3

v0.2.2

What's Changed

• Fixes to Wav2vec2 model by @lucasnewman in #135
• Fix Spark mel spec by @lucasnewman in #136
• More fixes for the Spark BiCodec module by @lucasnewman in #137
• Compatibility with MLX Swift 0.25.2 , add Swift Package by @yarshure in #138
• Remove model not found and fix swift GH actions by @Blaizzy in #146
• Fix deps by @Blaizzy in #147
• Add pull request template by @nlauchande in #150
• Add auto sampling rate by @Blaizzy in #148
• Add audio utilities, use them where possible by @lucasnewman in #161
• Fix join audio sample rate by @Blaizzy in #162
• Fix Spark voice matching by @lucasnewman in #163
• Fix Python memory spikes by @Blaizzy in #164
• Fix Kokoro ISTFT by @lucasnewman in #166
• Improvements to Sesame + Mimi streaming playback by @lucasnewman in #167
• Add Outtetts v1.0.0 by @Blaizzy in #168
• Fix Swift memory spikes by @Blaizzy in #165

New Contributors

• @yarshure made their first contribution in #138
• @nlauchande made their first contribution in #150

Full Changelog: v0.2.1...v0.2.2

v0.2.1

What's Changed

• Fix SparkTTS Detokenize (TTS) by @Blaizzy in #132

Full Changelog: v0.2.0...v0.2.1

v0.2.0

What's Changed

• Revert utils load and fix deprecate API by @Blaizzy in #98
• Remove all remaining torch calls by @lucasnewman in #95
• Dia: Split long inputs into individual two-speaker segments by @lucasnewman in #100
• Dia: Avoid extra allocations in kv cache by @lucasnewman in #103
• Add local version of Whisper for (STT) by @lucasnewman in #105
• Add streaming support for Sesame CSM by @lucasnewman in #107
• Add default voices for Sesame by @lucasnewman in #109
• Fix sesame loading and add mixed_3_4 quantisation by @Blaizzy in #113
• Add basic Modular Speech-To-Speech pipeline (CLI) by @lucasnewman in #111
• Add Spark-TTS by @Blaizzy in #92
• Fix SparkTTS Quant by @Blaizzy in #120
• Update spark.py by @Blaizzy in #121
• Add Parakeet (STT) by @Blaizzy in #122
• Improve Parakeet token merging by @senstella in #129
• Add MLX Swift Support and examples by @BenLumenDigital in #84
• Add wav2vec2 model (STT) for Spark by @lucasnewman in #131

New Contributors

• @senstella made their first contribution in #129
• @BenLumenDigital made their first contribution in #84

Full Changelog: v0.1.0...v0.2.0

v0.1.0

What's Changed

• Add support for OuteTTS 1.0 (v3) model by @lucasnewman in #86
• Feat: Add quantization and mixed quantization by @Blaizzy in #88
• Dia TTS model with voice cloning by @lucasnewman in #91 #93
• Handle strict argument in load_weights for better model compatibility by @kamillobinski in #94

New Contributors

• @kamillobinski made their first contribution in #94

Full Changelog: v0.0.4...v0.1.0

v0.0.4

What's Changed

• Add CSM (Conversational Speech Model) section to README.md by @ivanfioravanti in #56
• Use MLX-based SNAC vocoder for Orpheus by @lucasnewman in #62
• Add Descript neural audio codec by @lucasnewman in #57
• Vectorize overlap-add operation in istft by @lucasnewman in #66
• Align Orpheus sampling parameters with the reference implementation by @lucasnewman in #68
• Improve Korkoro generation performance by @lucasnewman in #73
• Add Speech to Speech Tab to the UI by @freddyaboulton in #79
• Add support for fp16 variant of Sesame by @lucasnewman in #78
• Add (partially-working) voice matching support for Orpheus by @lucasnewman in #75
• Bible Audiobook example by @andrepadez in #43
• removed push notification to ntfy by @andrepadez in #81
• Bump version by @Blaizzy in #82

New Contributors

• @freddyaboulton made their first contribution in #79

Full Changelog: v0.0.3...v0.0.4

v0.0.3

What's Changed

• Add verbose logging and model selection support by @ivanfioravanti in #22
• Pulsating effect by @ivanfioravanti in #23
• Compile the decoder for Kokoro by @lucasnewman in #24
• Play audio segments as they are generated by @lucasnewman in #26
• Evaluate the computation graph before returning results by @ivanfioravanti in #35
• Add Mimi neural audio codec by @lucasnewman in #34
• Add model for Sesame TTS by @lucasnewman in #36
• Sphere speed up during audio generation by @ivanfioravanti in #40
• Added more Voices by @andrepadez in #37
• Feature: External API for Audiobook Generation by @sergenes in #19
• Add EnCodec neural audio codec by @lucasnewman in #46
• Add Suno bark by @Blaizzy in #45
• Update README.md to fix lang_code error by @zboyles in #49
• fix model config by @Blaizzy in #50
• Add Vocos neural audio codec by @lucasnewman in #48
• Fix Kokoro audio generation by @lucasnewman in #52
• Add orpheus by @Blaizzy in #47
• Resample and Transcribe by @chigkim in #51
• Fix vocos config loading by @Blaizzy in #53

New Contributors

• @andrepadez made their first contribution in #37
• @sergenes made their first contribution in #19
• @zboyles made their first contribution in #49
• @chigkim made their first contribution in #51

Full Changelog: v0.0.2...v0.0.3

v0.0.2

What's Changed

• fix workflows and readme by @Blaizzy in #5
• Add soundfile to requirements and Quick Start in README by @ivanfioravanti in #8
• Remove librosa dependency by @lucasnewman in #11
• Add support for command-line playback with the --play argument by @lucasnewman in #10
• Allow receiving text input from stdin or an entry prompt by @lucasnewman in #12
• Add web server and improve audio player by @ivanfioravanti in #14
• Use phonemizer-fork to avoid espeak errors by @rampadc in #17

New Contributors

• @Blaizzy made their first contribution in #5
• @ivanfioravanti made their first contribution in #8
• @lucasnewman made their first contribution in #11
• @rampadc made their first contribution in #17

Full Changelog: v0.0.1...v0.0.2