kinescript-chatterbox 0.1.0__tar.gz → 0.1.1__tar.gz

{kinescript_chatterbox-0.1.0 → kinescript_chatterbox-0.1.1}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: kinescript-chatterbox
-Version: 0.1.0
-Summary: Chatterbox voices for kine voice: laughs and sighs from tags, cloned voices, and the time of each word
+Version: 0.1.1
+Summary: Chatterbox voices for kine voice: cloned voices, tags it acts some of the time, and the time of each word
 Author: Dr. Know How
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/drknowhow/kinescript/tree/main/plugins/kinescript-chatterbox
@@ -34,8 +34,8 @@ Dynamic: license-file
 
 [Chatterbox](https://github.com/resemble-ai/chatterbox) voices for `kine voice`, from Resemble AI's open models. It
 speaks the `text` of a scene's sounds into WAV files on your own machine and writes the time of each word, so
-layers can start on a word and captions follow the voice. Chatterbox Turbo acts on tags such as `[laugh]` and
-`[sigh]`, and either model can copy the voice of a short clip.
+layers can start on a word and captions follow the voice. Chatterbox Turbo takes tags such as `[laugh]` and
+`[sigh]`, though it acts them only some of the time (see Tags), and either model can copy the voice of a short clip.
 
 ```json
 {"id": "vo1", "role": "voice", "backend": "chatterbox",
@@ -90,6 +90,12 @@ A tag written the way ElevenLabs writes it, such as `[laughs]`, `[whispers]` or
 Turbo's `[laugh]`, `[whispering]` or `[clear throat]`, so one scene works with both. A tag Turbo does not know is left
 out, so it is not read aloud, and listed under `ignored` in what `kine voice` prints.
 
+Turbo acts its tags only some of the time. With the built-in voice and seeds 0 to 2, nine takes with `[laugh]`
+(three lines) had no sound where the laugh goes in three: a silent pause in two, no pause in one. The other six had
+sound there, not checked by ear. Seven takes with `[whispering]` never whispered: the words stayed 81 to 99% voiced,
+like plain speech (86 to 96%), where ElevenLabs' whisper is 1% voiced. Listen to a tagged line before you rely on
+it, try another `seed` in `options`, or give that sound `"backend": "elevenlabs"`.
+
 ## Voices and settings
 
 `speaker` is a WAV clip of 5 s or more, relative to the scene file, whose voice Chatterbox copies. Without one it

{kinescript_chatterbox-0.1.0 → kinescript_chatterbox-0.1.1}/README.md

@@ -2,8 +2,8 @@
 
 [Chatterbox](https://github.com/resemble-ai/chatterbox) voices for `kine voice`, from Resemble AI's open models. It
 speaks the `text` of a scene's sounds into WAV files on your own machine and writes the time of each word, so
-layers can start on a word and captions follow the voice. Chatterbox Turbo acts on tags such as `[laugh]` and
-`[sigh]`, and either model can copy the voice of a short clip.
+layers can start on a word and captions follow the voice. Chatterbox Turbo takes tags such as `[laugh]` and
+`[sigh]`, though it acts them only some of the time (see Tags), and either model can copy the voice of a short clip.
 
 ```json
 {"id": "vo1", "role": "voice", "backend": "chatterbox",
@@ -58,6 +58,12 @@ A tag written the way ElevenLabs writes it, such as `[laughs]`, `[whispers]` or
 Turbo's `[laugh]`, `[whispering]` or `[clear throat]`, so one scene works with both. A tag Turbo does not know is left
 out, so it is not read aloud, and listed under `ignored` in what `kine voice` prints.
 
+Turbo acts its tags only some of the time. With the built-in voice and seeds 0 to 2, nine takes with `[laugh]`
+(three lines) had no sound where the laugh goes in three: a silent pause in two, no pause in one. The other six had
+sound there, not checked by ear. Seven takes with `[whispering]` never whispered: the words stayed 81 to 99% voiced,
+like plain speech (86 to 96%), where ElevenLabs' whisper is 1% voiced. Listen to a tagged line before you rely on
+it, try another `seed` in `options`, or give that sound `"backend": "elevenlabs"`.
+
 ## Voices and settings
 
 `speaker` is a WAV clip of 5 s or more, relative to the scene file, whose voice Chatterbox copies. Without one it

{kinescript_chatterbox-0.1.0 → kinescript_chatterbox-0.1.1}/kinescript_chatterbox/__init__.py

@@ -14,7 +14,7 @@ from pathlib import Path
 
 from .align import TAG, align
 
-MODELS = ("turbo", "standard")  # turbo acts on tags; standard takes exaggeration and cfg_weight instead
+MODELS = ("turbo", "standard")  # turbo takes tags (acts some); standard takes exaggeration and cfg_weight instead
 TURBO_TAGS: set[str] = set()  # filled from Turbo's tokenizer when it loads
 OPTIONS = {"turbo": {"temperature", "top_p", "top_k", "repetition_penalty"},
            "standard": {"exaggeration", "cfg_weight", "temperature", "min_p", "top_p", "repetition_penalty"}}

{kinescript_chatterbox-0.1.0 → kinescript_chatterbox-0.1.1}/kinescript_chatterbox.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: kinescript-chatterbox
-Version: 0.1.0
-Summary: Chatterbox voices for kine voice: laughs and sighs from tags, cloned voices, and the time of each word
+Version: 0.1.1
+Summary: Chatterbox voices for kine voice: cloned voices, tags it acts some of the time, and the time of each word
 Author: Dr. Know How
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/drknowhow/kinescript/tree/main/plugins/kinescript-chatterbox
@@ -34,8 +34,8 @@ Dynamic: license-file
 
 [Chatterbox](https://github.com/resemble-ai/chatterbox) voices for `kine voice`, from Resemble AI's open models. It
 speaks the `text` of a scene's sounds into WAV files on your own machine and writes the time of each word, so
-layers can start on a word and captions follow the voice. Chatterbox Turbo acts on tags such as `[laugh]` and
-`[sigh]`, and either model can copy the voice of a short clip.
+layers can start on a word and captions follow the voice. Chatterbox Turbo takes tags such as `[laugh]` and
+`[sigh]`, though it acts them only some of the time (see Tags), and either model can copy the voice of a short clip.
 
 ```json
 {"id": "vo1", "role": "voice", "backend": "chatterbox",
@@ -90,6 +90,12 @@ A tag written the way ElevenLabs writes it, such as `[laughs]`, `[whispers]` or
 Turbo's `[laugh]`, `[whispering]` or `[clear throat]`, so one scene works with both. A tag Turbo does not know is left
 out, so it is not read aloud, and listed under `ignored` in what `kine voice` prints.
 
+Turbo acts its tags only some of the time. With the built-in voice and seeds 0 to 2, nine takes with `[laugh]`
+(three lines) had no sound where the laugh goes in three: a silent pause in two, no pause in one. The other six had
+sound there, not checked by ear. Seven takes with `[whispering]` never whispered: the words stayed 81 to 99% voiced,
+like plain speech (86 to 96%), where ElevenLabs' whisper is 1% voiced. Listen to a tagged line before you rely on
+it, try another `seed` in `options`, or give that sound `"backend": "elevenlabs"`.
+
 ## Voices and settings
 
 `speaker` is a WAV clip of 5 s or more, relative to the scene file, whose voice Chatterbox copies. Without one it

{kinescript_chatterbox-0.1.0 → kinescript_chatterbox-0.1.1}/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "kinescript-chatterbox"
-version = "0.1.0"
-description = "Chatterbox voices for kine voice: laughs and sighs from tags, cloned voices, and the time of each word"
+version = "0.1.1"
+description = "Chatterbox voices for kine voice: cloned voices, tags it acts some of the time, and the time of each word"
 readme = "README.md"
 license = "MIT"
 license-files = ["LICENSE"]