From 3d2645b8a4cc7471924e940b4203e168bf5b487d Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 12:39:16 +0100 Subject: [PATCH 01/27] Update requirements.txt --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 37bfbb3..6526b8a 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,7 @@ num2words spacy espeakng_loader -misaki[en]>=0.9.4 +misaki[en] onnxruntime soundfile numpy From e6b92e90ef0b485927177f782d18f28af8946473 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 12:56:04 +0100 Subject: [PATCH 02/27] Update requirements.txt --- requirements.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 6526b8a..d3f8388 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,7 @@ num2words spacy espeakng_loader -misaki[en] +git+https://github.com/hexgrad/misaki onnxruntime soundfile numpy From 0ff3e1647b39bff804c88130b1158d1e960a9d58 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:06:56 +0100 Subject: [PATCH 03/27] Update setup.py --- setup.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 5ff10c6..a976bff 100644 --- a/setup.py +++ b/setup.py @@ -24,6 +24,7 @@ "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Programming Language :: Python :: 3.12", + "Programming Language :: Python :: 3.13", "Topic :: Multimedia :: Sound/Audio :: Speech", "Topic :: Scientific/Engineering :: Artificial Intelligence", ], @@ -32,7 +33,7 @@ "num2words", "spacy", "espeakng_loader", - "misaki[en]>=0.9.4", + "git+https://github.com/hexgrad/misaki", "onnxruntime", "soundfile", "numpy", From b57ba62bc19b9ad6a14814e20819b1a17c49059c Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:08:07 +0100 Subject: [PATCH 04/27] Update pyproject.toml --- pyproject.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 8a60547..2895124 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -21,7 +21,7 @@ dependencies = [ "num2words", "spacy", "espeakng_loader", - "misaki[en]>=0.9.4", + "git+https://github.com/hexgrad/misaki", "onnxruntime", "soundfile", "numpy", From b8def04a8c8fb6e0dd0cb700b5e9a6e9ae690591 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:11:42 +0100 Subject: [PATCH 05/27] Update setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index a976bff..2b452b4 100644 --- a/setup.py +++ b/setup.py @@ -33,7 +33,7 @@ "num2words", "spacy", "espeakng_loader", - "git+https://github.com/hexgrad/misaki", + "misaki@git+https://github.com/hexgrad/misaki", "onnxruntime", "soundfile", "numpy", From 4fa325226039934f882a75a1d7f98d9f8ffaa640 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:11:58 +0100 Subject: [PATCH 06/27] Update pyproject.toml --- pyproject.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 2895124..51a4173 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -21,7 +21,7 @@ dependencies = [ "num2words", "spacy", "espeakng_loader", - "git+https://github.com/hexgrad/misaki", + "misaki@git+https://github.com/hexgrad/misaki", "onnxruntime", "soundfile", "numpy", From bb3da043f89c1d1e65fb8f80d01393349d481e3e Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:26:45 +0100 Subject: [PATCH 07/27] Update requirements.txt --- requirements.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/requirements.txt b/requirements.txt index d3f8388..c7aeaa2 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,3 +6,4 @@ onnxruntime soundfile numpy huggingface_hub +transformers From 54e58e9e1054255a0c66b6ce85a18109eaeebb0e Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:27:07 +0100 Subject: [PATCH 08/27] Update pyproject.toml --- pyproject.toml | 1 + 1 file changed, 1 insertion(+) diff --git a/pyproject.toml b/pyproject.toml index 51a4173..04ffe8a 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -26,6 +26,7 @@ dependencies = [ "soundfile", "numpy", "huggingface_hub", + "transformers" ] [project.urls] From 9d4c90565c0fd94066ef4d701a516767e6cbdee5 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:27:27 +0100 Subject: [PATCH 09/27] Update setup.py --- setup.py | 1 + 1 file changed, 1 insertion(+) diff --git a/setup.py b/setup.py index 2b452b4..ff92e4f 100644 --- a/setup.py +++ b/setup.py @@ -38,6 +38,7 @@ "soundfile", "numpy", "huggingface_hub", + "transformers", ], keywords="text-to-speech, tts, speech-synthesis, neural-networks, onnx", project_urls={ From ff261c146566c5561f925df114905bc272b18263 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:29:31 +0100 Subject: [PATCH 10/27] Update setup.py --- setup.py | 1 + 1 file changed, 1 insertion(+) diff --git a/setup.py b/setup.py index ff92e4f..df17a43 100644 --- a/setup.py +++ b/setup.py @@ -39,6 +39,7 @@ "numpy", "huggingface_hub", "transformers", + "torch", ], keywords="text-to-speech, tts, speech-synthesis, neural-networks, onnx", project_urls={ From e5b8cf8d2d945fc123ba726cc13ac612ee0f2e9b Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:29:47 +0100 Subject: [PATCH 11/27] Update pyproject.toml --- pyproject.toml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 04ffe8a..9566942 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -26,7 +26,8 @@ dependencies = [ "soundfile", "numpy", "huggingface_hub", - "transformers" + "transformers", + "torch" ] [project.urls] From 561a23141a07cc87a1892cff725126508253f80e Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:30:01 +0100 Subject: [PATCH 12/27] Update requirements.txt --- requirements.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/requirements.txt b/requirements.txt index c7aeaa2..d69d2bb 100644 --- a/requirements.txt +++ b/requirements.txt @@ -7,3 +7,4 @@ soundfile numpy huggingface_hub transformers +torch From 4ede476db5b839c5f7c8fc89ea2ec7436b934a65 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:44:53 +0100 Subject: [PATCH 13/27] Update requirements.txt --- requirements.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/requirements.txt b/requirements.txt index d69d2bb..e6b33e1 100644 --- a/requirements.txt +++ b/requirements.txt @@ -8,3 +8,4 @@ numpy huggingface_hub transformers torch +phonemizer-fork From 438053fb339c3997627c9eb7c975a0dc81cd805c Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:45:17 +0100 Subject: [PATCH 14/27] Update setup.py --- setup.py | 1 + 1 file changed, 1 insertion(+) diff --git a/setup.py b/setup.py index df17a43..b170b2f 100644 --- a/setup.py +++ b/setup.py @@ -40,6 +40,7 @@ "huggingface_hub", "transformers", "torch", + "phonemizer-fork", ], keywords="text-to-speech, tts, speech-synthesis, neural-networks, onnx", project_urls={ From ef5785330ce2f44c37cbeba8d77dfc8f9bf55e74 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Mon, 2 Mar 2026 13:45:29 +0100 Subject: [PATCH 15/27] Update pyproject.toml --- pyproject.toml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 9566942..a04a52c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -27,7 +27,8 @@ dependencies = [ "numpy", "huggingface_hub", "transformers", - "torch" + "torch", + "phonemizer-fork" ] [project.urls] From 999dc0c2b60c267273d217827a2551fe2f033f03 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Wed, 4 Mar 2026 11:37:09 +0100 Subject: [PATCH 16/27] Update requirements.txt --- requirements.txt | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/requirements.txt b/requirements.txt index e6b33e1..11577b2 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,11 +1,10 @@ num2words spacy espeakng_loader -git+https://github.com/hexgrad/misaki +git+https://github.com/createcandle/misaki onnxruntime soundfile numpy huggingface_hub transformers -torch phonemizer-fork From c1dfe88a720eb849e4ab6e331dda93149e872b14 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Wed, 4 Mar 2026 11:40:08 +0100 Subject: [PATCH 17/27] Update setup.py --- setup.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/setup.py b/setup.py index b170b2f..8e997a0 100644 --- a/setup.py +++ b/setup.py @@ -33,13 +33,12 @@ "num2words", "spacy", "espeakng_loader", - "misaki@git+https://github.com/hexgrad/misaki", + "misaki@git+https://github.com/createcandle/misaki", "onnxruntime", "soundfile", "numpy", "huggingface_hub", "transformers", - "torch", "phonemizer-fork", ], keywords="text-to-speech, tts, speech-synthesis, neural-networks, onnx", From c12243990a7eacad5844d12faa94d7115362bd97 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Wed, 4 Mar 2026 11:41:55 +0100 Subject: [PATCH 18/27] Update pyproject.toml --- pyproject.toml | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/pyproject.toml b/pyproject.toml index a04a52c..c16a6a0 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -21,13 +21,12 @@ dependencies = [ "num2words", "spacy", "espeakng_loader", - "misaki@git+https://github.com/hexgrad/misaki", + "misaki@git+https://github.com/createcandle/misaki", "onnxruntime", "soundfile", "numpy", "huggingface_hub", "transformers", - "torch", "phonemizer-fork" ] From bff4a54a2533f40f08b48eaa336de169a14db62b Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Wed, 4 Mar 2026 11:43:11 +0100 Subject: [PATCH 19/27] Update README.md --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 1a15bd3..fcdf59b 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,9 @@ # Kitten TTS 😻 +THIS IS A MODIFIED VERSION +- modified to be able to install on Python 3.13 +- modified to remove a dependency on Torch + Screenshot 2026-02-18 at 8 33 04 PM From 7b37963592f3569ee040900a88dfd0b88df84b65 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Wed, 4 Mar 2026 11:44:35 +0100 Subject: [PATCH 20/27] Update README.md --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index fcdf59b..ef7ba45 100644 --- a/README.md +++ b/README.md @@ -4,6 +4,9 @@ THIS IS A MODIFIED VERSION - modified to be able to install on Python 3.13 - modified to remove a dependency on Torch +It was modified in order to explore using it in: +https://github.com/createcandle/voco + Screenshot 2026-02-18 at 8 33 04 PM From f1fd3410c6849203bfac3cc28d36e0d1c82e6507 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 18:25:16 +0100 Subject: [PATCH 21/27] Update get_model.py --- kittentts/get_model.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kittentts/get_model.py b/kittentts/get_model.py index e9b346d..10bbd36 100644 --- a/kittentts/get_model.py +++ b/kittentts/get_model.py @@ -34,7 +34,7 @@ def generate(self, text, voice="expr-voice-5-m", speed=1.0, clean_text=False): Returns: Audio data as numpy array """ - print(f"Generating audio for text: {text}") + #print(f"Generating audio for text: {text}") return self.model.generate(text, voice=voice, speed=speed, clean_text=clean_text) def generate_to_file(self, text, output_path, voice="expr-voice-5-m", speed=1.0, sample_rate=24000): From 110f8f768dd2a3731f7ac031aed248ff462320f8 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 19:34:06 +0100 Subject: [PATCH 22/27] Update requirements.txt --- requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 11577b2..3f914a7 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,7 +1,6 @@ num2words spacy espeakng_loader -git+https://github.com/createcandle/misaki onnxruntime soundfile numpy From cc55b4c4f7507c51b6543c1ff78e437bf3360569 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 19:34:23 +0100 Subject: [PATCH 23/27] Update setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 8e997a0..23bf445 100644 --- a/setup.py +++ b/setup.py @@ -33,7 +33,7 @@ "num2words", "spacy", "espeakng_loader", - "misaki@git+https://github.com/createcandle/misaki", + #"misaki@git+https://github.com/createcandle/misaki", "onnxruntime", "soundfile", "numpy", From cb5099526ac78266e6411da5ed94af72e11b0632 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 19:39:20 +0100 Subject: [PATCH 24/27] Update pyproject.toml --- pyproject.toml | 1 - 1 file changed, 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index c16a6a0..76b15ed 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -21,7 +21,6 @@ dependencies = [ "num2words", "spacy", "espeakng_loader", - "misaki@git+https://github.com/createcandle/misaki", "onnxruntime", "soundfile", "numpy", From 964c5c803f3391980d3a70b8a3450bdc332db2b5 Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 19:41:44 +0100 Subject: [PATCH 25/27] Update setup.py --- setup.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/setup.py b/setup.py index 23bf445..eaaf62b 100644 --- a/setup.py +++ b/setup.py @@ -31,7 +31,7 @@ python_requires=">=3.8", install_requires=[ "num2words", - "spacy", + #"spacy", "espeakng_loader", #"misaki@git+https://github.com/createcandle/misaki", "onnxruntime", From 9361f7d11175b349dc7d4dd625e0ccd436a688ba Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 19:41:57 +0100 Subject: [PATCH 26/27] Update pyproject.toml --- pyproject.toml | 1 - 1 file changed, 1 deletion(-) diff --git a/pyproject.toml b/pyproject.toml index 76b15ed..43f08d2 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -19,7 +19,6 @@ classifiers = [ ] dependencies = [ "num2words", - "spacy", "espeakng_loader", "onnxruntime", "soundfile", From a9defffd6ffc7eceee3fe609578b501f03398aff Mon Sep 17 00:00:00 2001 From: flatsiedatsie Date: Thu, 5 Mar 2026 19:42:07 +0100 Subject: [PATCH 27/27] Update requirements.txt --- requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 3f914a7..3b61c2b 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,4 @@ num2words -spacy espeakng_loader onnxruntime soundfile