From 552ed166a8f6681d9140adb7cf734a50e521da2b Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 29 Apr 2025 10:01:21 +0530
Subject: [PATCH 01/19] feat: add transcode

---
 videodb/__about__.py  |  2 +-
 videodb/__init__.py   |  8 ++++++++
 videodb/_constants.py | 26 ++++++++++++++++++++++++++
 videodb/client.py     | 38 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 73 insertions(+), 1 deletion(-)

diff --git a/videodb/__about__.py b/videodb/__about__.py
index 972eedd..90f7f66 100644
--- a/videodb/__about__.py
+++ b/videodb/__about__.py
@@ -1,7 +1,7 @@
 """ About information for videodb sdk"""
 
 
-__version__ = "0.2.13"
+__version__ = "0.2.14"
 __title__ = "videodb"
 __author__ = "videodb"
 __email__ = "contact@videodb.io"
diff --git a/videodb/__init__.py b/videodb/__init__.py
index 6f13816..d1d3215 100644
--- a/videodb/__init__.py
+++ b/videodb/__init__.py
@@ -16,6 +16,10 @@
     SubtitleBorderStyle,
     SubtitleStyle,
     TextStyle,
+    TranscodeMode,
+    ResizeMode,
+    VideoConfig,
+    AudioConfig,
 )
 from videodb.client import Connection
 from videodb.exceptions import (
@@ -43,6 +47,10 @@
     "TextStyle",
     "SceneExtractionType",
     "Segmenter",
+    "TranscodeMode",
+    "ResizeMode",
+    "VideoConfig",
+    "AudioConfig",
 ]
 
 
diff --git a/videodb/_constants.py b/videodb/_constants.py
index b155752..b0eafbe 100644
--- a/videodb/_constants.py
+++ b/videodb/_constants.py
@@ -76,6 +76,7 @@ class ApiPath:
     web = "web"
     translate = "translate"
     dub = "dub"
+    transcode = "transcode"
 
 
 class Status:
@@ -164,3 +165,28 @@ class TextStyle:
     tabsize: int = 4
     x: Union[str, int] = "(main_w-text_w)/2"
     y: Union[str, int] = "(main_h-text_h)/2"
+
+
+class TranscodeMode:
+    lightning = "lightning"
+    economy = "economy"
+
+
+class ResizeMode:
+    crop = "crop"
+    fit = "fit"
+    pad = "pad"
+
+
+@dataclass
+class VideoConfig:
+    resolution: int = 720
+    quality: int = 23
+    framerate: int = None
+    aspect_ratio: str = None
+    resize_mode: str = ResizeMode.crop
+
+
+@dataclass
+class AudioConfig:
+    mute: bool = False
diff --git a/videodb/client.py b/videodb/client.py
index 7cbfbfd..54fe008 100644
--- a/videodb/client.py
+++ b/videodb/client.py
@@ -8,6 +8,9 @@
 from videodb.__about__ import __version__
 from videodb._constants import (
     ApiPath,
+    TranscodeMode,
+    VideoConfig,
+    AudioConfig,
 )
 
 from videodb.collection import Collection
@@ -188,6 +191,41 @@ def youtube_search(
         )
         return search_data.get("results")
 
+    def transcode(
+        self,
+        source: str,
+        callback_url: str,
+        mode: TranscodeMode = TranscodeMode.economy,
+        start_ts: int = None,
+        end_ts: int = None,
+        video_config: VideoConfig = VideoConfig(),
+        audio_config: AudioConfig = AudioConfig(),
+    ) -> None:
+        """Transcode the video
+
+        :param str source: URL of the video to transcode, preferably a downloadable URL
+        :param str callback_url: URL to receive the callback
+        :param TranscodeMode mode: Mode of the transcoding
+        :param int start_ts: Start timestamp of the video to transcode (optional)
+        :param int end_ts: End timestamp of the video to transcode (optional)
+        :param VideoConfig video_config: Video configuration (optional)
+        :param AudioConfig audio_config: Audio configuration (optional)
+        :return: None
+        :rtype: None
+        """
+        self.post(
+            path=f"{ApiPath.transcode}",
+            data={
+                "source": source,
+                "callback_url": callback_url,
+                "mode": mode,
+                "start_ts": start_ts,
+                "end_ts": end_ts,
+                "video_config": video_config.__dict__,
+                "audio_config": audio_config.__dict__,
+            },
+        )
+
     def upload(
         self,
         file_path: str = None,

From 55269c97083323dcb1ceb4e787a1488f7bdfad94 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 6 May 2025 15:14:40 +0530
Subject: [PATCH 02/19] refactor: start and end

---
 videodb/client.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/videodb/client.py b/videodb/client.py
index 54fe008..f0e5c26 100644
--- a/videodb/client.py
+++ b/videodb/client.py
@@ -196,8 +196,8 @@ def transcode(
         source: str,
         callback_url: str,
         mode: TranscodeMode = TranscodeMode.economy,
-        start_ts: int = None,
-        end_ts: int = None,
+        start: int = None,
+        end: int = None,
         video_config: VideoConfig = VideoConfig(),
         audio_config: AudioConfig = AudioConfig(),
     ) -> None:
@@ -206,8 +206,8 @@ def transcode(
         :param str source: URL of the video to transcode, preferably a downloadable URL
         :param str callback_url: URL to receive the callback
         :param TranscodeMode mode: Mode of the transcoding
-        :param int start_ts: Start timestamp of the video to transcode (optional)
-        :param int end_ts: End timestamp of the video to transcode (optional)
+        :param int start: Start timestamp of the video to transcode (optional)
+        :param int end: End timestamp of the video to transcode (optional)
         :param VideoConfig video_config: Video configuration (optional)
         :param AudioConfig audio_config: Audio configuration (optional)
         :return: None
@@ -219,8 +219,8 @@ def transcode(
                 "source": source,
                 "callback_url": callback_url,
                 "mode": mode,
-                "start_ts": start_ts,
-                "end_ts": end_ts,
+                "start": start,
+                "end": end,
                 "video_config": video_config.__dict__,
                 "audio_config": audio_config.__dict__,
             },

From 808b8fdef764867c0cf9ab772d1269e908c2b833 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 10 Jun 2025 19:14:50 +0530
Subject: [PATCH 03/19] feat: add transcode details

---
 videodb/client.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/videodb/client.py b/videodb/client.py
index f0e5c26..528bfdf 100644
--- a/videodb/client.py
+++ b/videodb/client.py
@@ -226,6 +226,15 @@ def transcode(
             },
         )
 
+    def get_transcode_details(self, job_id: str) -> dict:
+        """Get the details of a transcode job.
+
+        :param str job_id: ID of the transcode job
+        :return: Details of the transcode job
+        :rtype: dict
+        """
+        return self.get(path=f"{ApiPath.transcode}/{job_id}")
+
     def upload(
         self,
         file_path: str = None,

From 80f4541966b66199ace6811d5ed834577a7485eb Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 10 Jun 2025 19:18:13 +0530
Subject: [PATCH 04/19] fix: constants

---
 videodb/_constants.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/videodb/_constants.py b/videodb/_constants.py
index b0eafbe..a4415b2 100644
--- a/videodb/_constants.py
+++ b/videodb/_constants.py
@@ -180,7 +180,7 @@ class ResizeMode:
 
 @dataclass
 class VideoConfig:
-    resolution: int = 720
+    resolution: int = None
     quality: int = 23
     framerate: int = None
     aspect_ratio: str = None

From 24711acbc9ab52ac7017e2439a6229d524a8f138 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 10 Jun 2025 19:26:12 +0530
Subject: [PATCH 05/19] feat: add job id

---
 videodb/client.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/videodb/client.py b/videodb/client.py
index 528bfdf..896eacd 100644
--- a/videodb/client.py
+++ b/videodb/client.py
@@ -213,7 +213,7 @@ def transcode(
         :return: None
         :rtype: None
         """
-        self.post(
+        job_data = self.post(
             path=f"{ApiPath.transcode}",
             data={
                 "source": source,
@@ -225,6 +225,7 @@ def transcode(
                 "audio_config": audio_config.__dict__,
             },
         )
+        return job_data.get("job_id")
 
     def get_transcode_details(self, job_id: str) -> dict:
         """Get the details of a transcode job.

From 1993b82c4804233f02827295cef95df1c3678aff Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 10 Jun 2025 19:29:28 +0530
Subject: [PATCH 06/19] build: update version

---
 videodb/__about__.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/videodb/__about__.py b/videodb/__about__.py
index 90f7f66..4059c8a 100644
--- a/videodb/__about__.py
+++ b/videodb/__about__.py
@@ -1,7 +1,7 @@
 """ About information for videodb sdk"""
 
 
-__version__ = "0.2.14"
+__version__ = "0.2.15"
 __title__ = "videodb"
 __author__ = "videodb"
 __email__ = "contact@videodb.io"

From fa73a1e939f6d710bc41bb5ebaf1cadb2b2970ba Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Wed, 11 Jun 2025 14:53:17 +0530
Subject: [PATCH 07/19] fix: remove ts

---
 videodb/client.py | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/videodb/client.py b/videodb/client.py
index 896eacd..a8818c2 100644
--- a/videodb/client.py
+++ b/videodb/client.py
@@ -196,8 +196,6 @@ def transcode(
         source: str,
         callback_url: str,
         mode: TranscodeMode = TranscodeMode.economy,
-        start: int = None,
-        end: int = None,
         video_config: VideoConfig = VideoConfig(),
         audio_config: AudioConfig = AudioConfig(),
     ) -> None:
@@ -206,8 +204,6 @@ def transcode(
         :param str source: URL of the video to transcode, preferably a downloadable URL
         :param str callback_url: URL to receive the callback
         :param TranscodeMode mode: Mode of the transcoding
-        :param int start: Start timestamp of the video to transcode (optional)
-        :param int end: End timestamp of the video to transcode (optional)
         :param VideoConfig video_config: Video configuration (optional)
         :param AudioConfig audio_config: Audio configuration (optional)
         :return: None
@@ -219,8 +215,6 @@ def transcode(
                 "source": source,
                 "callback_url": callback_url,
                 "mode": mode,
-                "start": start,
-                "end": end,
                 "video_config": video_config.__dict__,
                 "audio_config": audio_config.__dict__,
             },

From 5aa14a6a2d701b306f42f7de85e3ae1d33a2a020 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 12 Jun 2025 17:45:00 +0530
Subject: [PATCH 08/19] fix: doc strings

---
 videodb/client.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/videodb/client.py b/videodb/client.py
index 5bd7375..25ae399 100644
--- a/videodb/client.py
+++ b/videodb/client.py
@@ -230,8 +230,8 @@ def transcode(
         :param TranscodeMode mode: Mode of the transcoding
         :param VideoConfig video_config: Video configuration (optional)
         :param AudioConfig audio_config: Audio configuration (optional)
-        :return: None
-        :rtype: None
+        :return: Transcode job ID
+        :rtype: str
         """
         job_data = self.post(
             path=f"{ApiPath.transcode}",

From 8e79b159c9fee8e51ffe15a0f97745a1a95727f9 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Mon, 23 Jun 2025 12:54:46 +0530
Subject: [PATCH 09/19] feat: add timelinev2

---
 videodb/timeline_v2.py | 250 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 250 insertions(+)
 create mode 100644 videodb/timeline_v2.py

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
new file mode 100644
index 0000000..2f4732c
--- /dev/null
+++ b/videodb/timeline_v2.py
@@ -0,0 +1,250 @@
+from typing import List, Optional, Union
+from enum import Enum
+
+
+class AssetType(str, Enum):
+    video = "video"
+    image = "image"
+
+
+class Fit(str, Enum):
+    crop = "crop"
+    cover = "cover"
+    contain = "contain"
+    none = "none"
+
+
+class Position(str, Enum):
+    top = "top"
+    bottom = "bottom"
+    left = "left"
+    right = "right"
+    center = "center"
+    top_left = "top-left"
+    top_right = "top-right"
+    bottom_left = "bottom-left"
+    bottom_right = "bottom-right"
+
+
+class Filter(str, Enum):
+    """A filter effect to apply to the Clip."""
+
+    blur = "blur"
+    boost = "boost"
+    contrast = "contrast"
+    darken = "darken"
+    greyscale = "greyscale"
+    lighten = "lighten"
+    muted = "muted"
+    negative = "negative"
+
+
+class Offset:
+    def __init__(self, x: float = 0, y: float = 0):
+        self.x = x
+        self.y = y
+
+    def to_json(self):
+        return {
+            "x": self.x,
+            "y": self.y,
+        }
+
+
+class Crop:
+    def __init__(self, top: int = 0, right: int = 0, bottom: int = 0, left: int = 0):
+        self.top = top
+        self.right = right
+        self.bottom = bottom
+        self.left = left
+
+    def to_json(self):
+        return {
+            "top": self.top,
+            "right": self.right,
+            "bottom": self.bottom,
+            "left": self.left,
+        }
+
+
+class Transition:
+    def __init__(self, in_: str = None, out: str = None):
+        self.in_ = in_
+        self.out = out
+
+    def to_json(self):
+        return {
+            "in": self.in_,
+            "out": self.out,
+        }
+
+
+class BaseAsset:
+    """The type of asset to display for the duration of the Clip."""
+
+    type: AssetType
+
+
+class VideoAsset(BaseAsset):
+    """The VideoAsset is used to create video sequences from video files. The src must be a publicly accessible URL to a video resource"""
+
+    type = AssetType.video
+
+    def __init__(
+        self,
+        id: str,
+        trim: int = 0,
+        volume: float = 1,
+        crop: Optional[Crop] = None,
+    ):
+        if trim < 0:
+            raise ValueError("trim must be non-negative")
+        if not (0 <= volume <= 2):
+            raise ValueError("volume must be between 0 and 2")
+
+        self.id = id
+        self.trim = trim
+        self.volume = volume
+        self.crop = crop if crop is not None else Crop()
+
+    def to_json(self):
+        return {
+            "type": self.type,
+            "id": self.id,
+            "trim": self.trim,
+            "volume": self.volume,
+            "crop": self.crop.to_json(),
+        }
+
+
+class ImageAsset(BaseAsset):
+    """The ImageAsset is used to create video from images to compose an image. The src must be a publicly accessible URL to an image resource such as a jpg or png file."""
+
+    type = AssetType.image
+
+    def __init__(self, id: str, trim: int = 0, crop: Optional[Crop] = None):
+        if trim < 0:
+            raise ValueError("trim must be non-negative")
+
+        self.id = id
+        self.trim = trim
+        self.crop = crop if crop is not None else Crop()
+
+    def to_json(self):
+        return {
+            "type": self.type,
+            "id": self.id,
+            "trim": self.trim,
+            "crop": self.crop.to_json(),
+        }
+
+
+AnyAsset = Union[VideoAsset, ImageAsset]
+
+
+class Clip:
+    """A clip is a container for a specific type of asset, i.e. a title, image, video, audio or html. You use a Clip to define when an asset will display on the timeline, how long it will play for and transitions, filters and effects to apply to it."""
+
+    def __init__(
+        self,
+        asset: AnyAsset,
+        start: Union[float, int],
+        length: Union[float, int],
+        transition: Optional[Transition] = None,
+        effect: Optional[str] = None,
+        filter: Optional[Filter] = None,
+        scale: float = 1,
+        opacity: float = 1,
+        fit: Optional[Fit] = Fit.crop,
+        position: Position = Position.center,
+        offset: Optional[Offset] = None,
+    ):
+        if start < 0:
+            raise ValueError("start must be non-negative")
+        if length <= 0:
+            raise ValueError("length must be positive")
+        if not (0 <= scale <= 10):
+            raise ValueError("scale must be between 0 and 10")
+        if not (0 <= opacity <= 1):
+            raise ValueError("opacity must be between 0 and 1")
+
+        self.asset = asset
+        self.start = start
+        self.length = length
+        self.transition = transition
+        self.effect = effect
+        self.filter = filter
+        self.scale = scale
+        self.opacity = opacity
+        self.fit = fit
+        self.position = position
+        self.offset = offset if offset is not None else Offset()
+
+    def to_json(self):
+        json = {
+            "asset": self.asset.to_json(),
+            "start": self.start,
+            "length": self.length,
+            "effect": self.effect,
+            "scale": self.scale,
+            "opacity": self.opacity,
+            "fit": self.fit,
+            "position": self.position,
+            "offset": self.offset.to_json(),
+        }
+
+        if self.transition:
+            json["transition"] = self.transition.to_json()
+        if self.filter:
+            json["filter"] = self.filter.value
+
+        return json
+
+
+class Track:
+    clips: List[Clip]
+
+    def __init__(self, clips: List[Clip] = []):
+        self.clips = clips
+
+    def add_clip(self, clip: Clip):
+        self.clips.append(clip)
+
+    def to_json(self):
+        return {
+            "clips": [clip.to_json() for clip in self.clips],
+        }
+
+
+class TimelineV2:
+    def __init__(self, connection):
+        self.connection = connection
+        self.background: str = "#000000"
+        self.resolution: str = "1280x720"
+        self.tracks: List[Track] = []
+        self.stream_url = None
+        self.player_url = None
+
+    def add_track(self, track: Track):
+        self.tracks.append(track)
+
+    def add_clip(self, track_index: int, clip: Clip):
+        self.tracks[track_index].clips.append(clip)
+
+    def to_json(self):
+        return {
+            "timeline": {
+                "background": self.background,
+                "resolution": self.resolution,
+                "tracks": [track.to_json() for track in self.tracks],
+            }
+        }
+
+    def generate_stream(self):
+        stream_data = self.connection.post(
+            path="timeline_v2",
+            data=self.to_json(),
+        )
+        self.stream_url = stream_data.get("stream_url")
+        self.player_url = stream_data.get("player_url")
+        return stream_data.get("stream_url", None)

From a8fdf4ee943f4d977851e130189730a729a6459e Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Mon, 23 Jun 2025 14:28:13 +0530
Subject: [PATCH 10/19] fix: fit

---
 videodb/timeline_v2.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index 2f4732c..8e973d0 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -11,7 +11,6 @@ class Fit(str, Enum):
     crop = "crop"
     cover = "cover"
     contain = "contain"
-    none = "none"
 
 
 class Position(str, Enum):

From 1e4a5f61259e3979853fbef4c605e03923a6e30f Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Mon, 23 Jun 2025 15:24:41 +0530
Subject: [PATCH 11/19] build: update v

---
 videodb/__about__.py   | 2 +-
 videodb/timeline_v2.py | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/videodb/__about__.py b/videodb/__about__.py
index 3cc2806..fe85f3d 100644
--- a/videodb/__about__.py
+++ b/videodb/__about__.py
@@ -2,7 +2,7 @@
 
 
 
-__version__ = "0.2.15"
+__version__ = "0.2.16"
 __title__ = "videodb"
 __author__ = "videodb"
 __email__ = "contact@videodb.io"
diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index 8e973d0..c6b82ba 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -201,8 +201,6 @@ def to_json(self):
 
 
 class Track:
-    clips: List[Clip]
-
     def __init__(self, clips: List[Clip] = []):
         self.clips = clips
 

From 2b51bfc22c2a13009ef4aa11bd9d301f972d4e98 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 26 Jun 2025 10:12:58 +0530
Subject: [PATCH 12/19] fix: image asset

---
 videodb/timeline_v2.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index c6b82ba..8c98e65 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -133,7 +133,6 @@ def to_json(self):
         return {
             "type": self.type,
             "id": self.id,
-            "trim": self.trim,
             "crop": self.crop.to_json(),
         }
 

From 2940995c6b67985c538ea5123f0aefc7f07d0713 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Wed, 2 Jul 2025 18:30:39 +0530
Subject: [PATCH 13/19] feat: add audio asset

---
 videodb/__about__.py   |  2 +-
 videodb/timeline_v2.py | 21 ++++++++++++++++++++-
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/videodb/__about__.py b/videodb/__about__.py
index fe85f3d..1a52acf 100644
--- a/videodb/__about__.py
+++ b/videodb/__about__.py
@@ -2,7 +2,7 @@
 
 
 
-__version__ = "0.2.16"
+__version__ = "0.2.17"
 __title__ = "videodb"
 __author__ = "videodb"
 __email__ = "contact@videodb.io"
diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index 8c98e65..b323893 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -137,7 +137,26 @@ def to_json(self):
         }
 
 
-AnyAsset = Union[VideoAsset, ImageAsset]
+class AudioAsset(BaseAsset):
+    """The AudioAsset is used to create audio sequences from audio files. The src must be a publicly accessible URL to an audio resource"""
+
+    type = AssetType.audio
+
+    def __init__(self, id: str, trim: int = 0, volume: float = 1):
+        self.id = id
+        self.trim = trim
+        self.volume = volume
+
+    def to_json(self):
+        return {
+            "type": self.type,
+            "id": self.id,
+            "trim": self.trim,
+            "volume": self.volume,
+        }
+
+
+AnyAsset = Union[VideoAsset, ImageAsset, AudioAsset]
 
 
 class Clip:

From 2672b729ab597b09986e73459b02d864e022b8dc Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Wed, 2 Jul 2025 18:35:43 +0530
Subject: [PATCH 14/19] fix: asset enum

---
 videodb/timeline_v2.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index b323893..5482cad 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -5,6 +5,7 @@
 class AssetType(str, Enum):
     video = "video"
     image = "image"
+    audio = "audio"
 
 
 class Fit(str, Enum):

From 3537e396d00e4210229883275cc5cb642e561fec Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 8 Jul 2025 13:07:45 +0530
Subject: [PATCH 15/19] feat: add text asset

---
 videodb/timeline_v2.py | 223 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 222 insertions(+), 1 deletion(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index 5482cad..f2e01c0 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -6,6 +6,7 @@ class AssetType(str, Enum):
     video = "video"
     image = "image"
     audio = "audio"
+    text = "text"
 
 
 class Fit(str, Enum):
@@ -39,6 +40,36 @@ class Filter(str, Enum):
     negative = "negative"
 
 
+class TextAlignment(str, Enum):
+    """Place the text in one of nine predefined positions of the background."""
+
+    top = "top"
+    top_right = "top_right"
+    right = "right"
+    bottom_right = "bottom_right"
+    bottom = "bottom"
+    bottom_left = "bottom_left"
+    left = "left"
+    top_left = "top_left"
+    center = "center"
+
+
+class HorizontalAlignment(str, Enum):
+    """Horizontal text alignment options."""
+
+    left = "left"
+    center = "center"
+    right = "right"
+
+
+class VerticalAlignment(str, Enum):
+    """Vertical text alignment options."""
+
+    top = "top"
+    center = "center"
+    bottom = "bottom"
+
+
 class Offset:
     def __init__(self, x: float = 0, y: float = 0):
         self.x = x
@@ -157,7 +188,197 @@ def to_json(self):
         }
 
 
-AnyAsset = Union[VideoAsset, ImageAsset, AudioAsset]
+class Font:
+    """Font styling properties for text assets."""
+
+    def __init__(
+        self,
+        family: str = "Clear Sans",
+        size: int = 48,
+        color: str = "#FFFFFF",
+        opacity: float = 1.0,
+        weight: Optional[int] = None,
+    ):
+        if size < 1:
+            raise ValueError("size must be at least 1")
+        if not (0.0 <= opacity <= 1.0):
+            raise ValueError("opacity must be between 0.0 and 1.0")
+        if weight is not None and not (100 <= weight <= 900):
+            raise ValueError("weight must be between 100 and 900")
+
+        self.family = family
+        self.size = size
+        self.color = color
+        self.opacity = opacity
+        self.weight = weight
+
+    def to_json(self):
+        data = {
+            "family": self.family,
+            "size": self.size,
+            "color": self.color,
+            "opacity": self.opacity,
+        }
+        if self.weight is not None:
+            data["weight"] = self.weight
+        return data
+
+
+class Border:
+    """Text border properties."""
+
+    def __init__(self, color: str = "#000000", width: float = 0.0):
+        if width < 0.0:
+            raise ValueError("width must be non-negative")
+        self.color = color
+        self.width = width
+
+    def to_json(self):
+        return {
+            "color": self.color,
+            "width": self.width,
+        }
+
+
+class Shadow:
+    """Text shadow properties."""
+
+    def __init__(self, color: str = "#000000", x: float = 0.0, y: float = 0.0):
+        if x < 0.0:
+            raise ValueError("x must be non-negative")
+        if y < 0.0:
+            raise ValueError("y must be non-negative")
+        self.color = color
+        self.x = x
+        self.y = y
+
+    def to_json(self):
+        return {
+            "color": self.color,
+            "x": self.x,
+            "y": self.y,
+        }
+
+
+class Background:
+    """Text background styling properties."""
+
+    def __init__(
+        self,
+        width: float = 0.0,
+        height: float = 0.0,
+        color: str = "#000000",
+        border_width: float = 0.0,
+        opacity: float = 1.0,
+        text_alignment: TextAlignment = TextAlignment.center,
+    ):
+        if width < 0.0:
+            raise ValueError("width must be non-negative")
+        if height < 0.0:
+            raise ValueError("height must be non-negative")
+        if border_width < 0.0:
+            raise ValueError("border_width must be non-negative")
+        if not (0.0 <= opacity <= 1.0):
+            raise ValueError("opacity must be between 0.0 and 1.0")
+
+        self.width = width
+        self.height = height
+        self.color = color
+        self.border_width = border_width
+        self.opacity = opacity
+        self.text_alignment = text_alignment
+
+    def to_json(self):
+        return {
+            "width": self.width,
+            "height": self.height,
+            "color": self.color,
+            "border_width": self.border_width,
+            "opacity": self.opacity,
+            "text_alignment": self.text_alignment.value,
+        }
+
+
+class Alignment:
+    """Text alignment properties."""
+
+    def __init__(
+        self,
+        horizontal: HorizontalAlignment = HorizontalAlignment.center,
+        vertical: VerticalAlignment = VerticalAlignment.center,
+    ):
+        self.horizontal = horizontal
+        self.vertical = vertical
+
+    def to_json(self):
+        return {
+            "horizontal": self.horizontal.value,
+            "vertical": self.vertical.value,
+        }
+
+
+class TextAsset(BaseAsset):
+    """The TextAsset is used to create text sequences from text strings with full control over the text styling and positioning."""
+
+    type = AssetType.text
+
+    def __init__(
+        self,
+        text: str,
+        font: Optional[Font] = None,
+        border: Optional[Border] = None,
+        shadow: Optional[Shadow] = None,
+        background: Optional[Background] = None,
+        alignment: Optional[Alignment] = None,
+        tabsize: int = 4,
+        line_spacing: float = 0,
+        width: Optional[int] = None,
+        height: Optional[int] = None,
+    ):
+        if tabsize < 1:
+            raise ValueError("tabsize must be at least 1")
+        if line_spacing < 0.0:
+            raise ValueError("line_spacing must be non-negative")
+        if width is not None and width < 1:
+            raise ValueError("width must be at least 1")
+        if height is not None and height < 1:
+            raise ValueError("height must be at least 1")
+
+        self.text = text
+        self.font = font if font is not None else Font()
+        self.border = border
+        self.shadow = shadow
+        self.background = background
+        self.alignment = alignment if alignment is not None else Alignment()
+        self.tabsize = tabsize
+        self.line_spacing = line_spacing
+        self.width = width
+        self.height = height
+
+    def to_json(self):
+        data = {
+            "type": self.type,
+            "text": self.text,
+            "font": self.font.to_json(),
+            "alignment": self.alignment.to_json(),
+            "tabsize": self.tabsize,
+            "line_spacing": self.line_spacing,
+        }
+        if self.border:
+            data["border"] = self.border.to_json()
+        if self.shadow:
+            data["shadow"] = self.shadow.to_json()
+        if self.background:
+            data["background"] = self.background.to_json()
+        if self.width is not None:
+            data["width"] = self.width
+        if self.height is not None:
+            data["height"] = self.height
+
+        return data
+
+
+AnyAsset = Union[VideoAsset, ImageAsset, AudioAsset, TextAsset]
 
 
 class Clip:

From ac78d552712e66e9e361dc01ac27378c3aed3551 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Thu, 17 Jul 2025 11:53:45 +0530
Subject: [PATCH 16/19] fix: volume range

---
 videodb/timeline_v2.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index f2e01c0..b74bc62 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -130,8 +130,8 @@ def __init__(
     ):
         if trim < 0:
             raise ValueError("trim must be non-negative")
-        if not (0 <= volume <= 2):
-            raise ValueError("volume must be between 0 and 2")
+        if not (0 <= volume <= 5):
+            raise ValueError("volume must be between 0 and 5")
 
         self.id = id
         self.trim = trim

From fcf4796ed6cfd18ba96209bddeffcb7686f9edc2 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 5 Aug 2025 11:09:52 +0530
Subject: [PATCH 17/19] feat: add caption asset

---
 videodb/timeline_v2.py | 168 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 167 insertions(+), 1 deletion(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index b74bc62..27c2903 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -7,6 +7,7 @@ class AssetType(str, Enum):
     image = "image"
     audio = "audio"
     text = "text"
+    caption = "caption"
 
 
 class Fit(str, Enum):
@@ -62,6 +63,40 @@ class HorizontalAlignment(str, Enum):
     right = "right"
 
 
+class CaptionBorderStyle(int, Enum):
+    """Border style properties for caption assets."""
+
+    no_border = 1
+    opaque_box = 3
+    outline = 4
+
+
+class CaptionAlignment(int, Enum):
+    """Caption alignment properties for caption assets."""
+
+    bottom_left = 1
+    bottom_center = 2
+    bottom_right = 3
+    middle_left = 9
+    middle_center = 10
+    middle_right = 11
+    top_left = 5
+    top_center = 6
+    top_right = 7
+
+
+class CaptionAnimation(str, Enum):
+    """Caption animation properties for caption assets."""
+
+    float_in_bottom = "float_in_bottom"
+    box_highlight = "box_highlight"
+    color_highlight = "color_highlight"
+    reveal = "reveal"
+    karioke = "karioke"
+    impact = "impact"
+    supersize = "supersize"
+
+
 class VerticalAlignment(str, Enum):
     """Vertical text alignment options."""
 
@@ -378,7 +413,138 @@ def to_json(self):
         return data
 
 
-AnyAsset = Union[VideoAsset, ImageAsset, AudioAsset, TextAsset]
+class FontStyling:
+    """Font styling properties for caption assets."""
+
+    def __init__(
+        self,
+        name: str = "Clear Sans",
+        size: int = 30,
+        bold: bool = False,
+        italic: bool = False,
+        underline: bool = False,
+        strikeout: bool = False,
+        scale_x: float = 1.0,
+        scale_y: float = 1.0,
+        spacing: float = 0.0,
+        angle: float = 0.0,
+    ):
+        self.name = name
+        self.size = size
+        self.bold = bold
+        self.italic = italic
+        self.underline = underline
+        self.strikeout = strikeout
+        self.scale_x = scale_x
+        self.scale_y = scale_y
+        self.spacing = spacing
+        self.angle = angle
+
+    def to_json(self):
+        return {
+            "font_name": self.name,
+            "font_size": self.size,
+            "bold": self.bold,
+            "italic": self.italic,
+            "underline": self.underline,
+            "strikeout": self.strikeout,
+            "scale_x": self.scale_x,
+            "scale_y": self.scale_y,
+            "spacing": self.spacing,
+            "angle": self.angle,
+        }
+
+
+class BorderAndShadow:
+    """Border and shadow properties for caption assets."""
+
+    def __init__(
+        self,
+        style: CaptionBorderStyle = CaptionBorderStyle.no_border,
+        outline: int = 1,
+        outline_color: str = "&H00000000",
+        shadow: int = 0,
+    ):
+        self.style = style
+        self.outline = outline
+        self.outline_color = outline_color
+        self.shadow = shadow
+
+    def to_json(self):
+        return {
+            "style": self.style.value,
+            "outline": self.outline,
+            "outline_color": self.outline_color,
+            "shadow": self.shadow,
+        }
+
+
+class Positioning:
+    """Positioning properties for caption assets."""
+
+    def __init__(
+        self,
+        alignment: CaptionAlignment = CaptionAlignment.bottom_center,
+        margin_l: int = 30,
+        margin_r: int = 30,
+        margin_v: int = 30,
+    ):
+        self.alignment = alignment
+        self.margin_l = margin_l
+        self.margin_r = margin_r
+        self.margin_v = margin_v
+
+    def to_json(self):
+        return {
+            "alignment": self.alignment.value,
+            "margin_l": self.margin_l,
+            "margin_r": self.margin_r,
+            "margin_v": self.margin_v,
+        }
+
+
+class CaptionAsset(BaseAsset):
+    """The CaptionAsset is used to create captions from text strings with full styling and ass support."""
+
+    type = AssetType.caption
+
+    def __init__(
+        self,
+        src: str = "auto",
+        font: Optional[FontStyling] = None,
+        primary_color: str = "&H00FFFFFF",
+        secondary_color: str = "&H000000FF",
+        back_color: str = "&H00000000",
+        border: Optional[BorderAndShadow] = None,
+        position: Optional[Positioning] = None,
+        animation: Optional[CaptionAnimation] = None,
+    ):
+        self.src = src
+        self.font = font if font is not None else FontStyling()
+        self.primary_color = primary_color
+        self.secondary_color = secondary_color
+        self.back_color = back_color
+        self.border = border if border is not None else BorderAndShadow()
+        self.position = position if position is not None else Positioning()
+        self.animation = animation
+
+    def to_json(self):
+        data = {
+            "type": self.type,
+            "src": self.src,
+            "font": self.font.to_json(),
+            "primary_color": self.primary_color,
+            "secondary_color": self.secondary_color,
+            "back_color": self.back_color,
+            "border": self.border.to_json(),
+            "position": self.position.to_json(),
+        }
+        if self.animation:
+            data["animation"] = self.animation.value
+        return data
+
+
+AnyAsset = Union[VideoAsset, ImageAsset, AudioAsset, TextAsset, CaptionAsset]
 
 
 class Clip:

From 9d5a6b0853485ca14270299cbf5cee9284747746 Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 5 Aug 2025 12:41:09 +0530
Subject: [PATCH 18/19] fix: caption animation

---
 videodb/timeline_v2.py | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index 27c2903..925d755 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -63,32 +63,32 @@ class HorizontalAlignment(str, Enum):
     right = "right"
 
 
-class CaptionBorderStyle(int, Enum):
+class CaptionBorderStyle(str, Enum):
     """Border style properties for caption assets."""
 
-    no_border = 1
-    opaque_box = 3
-    outline = 4
+    no_border = "no_border"
+    opaque_box = "opaque_box"
+    outline = "outline"
 
 
-class CaptionAlignment(int, Enum):
+class CaptionAlignment(str, Enum):
     """Caption alignment properties for caption assets."""
 
-    bottom_left = 1
-    bottom_center = 2
-    bottom_right = 3
-    middle_left = 9
-    middle_center = 10
-    middle_right = 11
-    top_left = 5
-    top_center = 6
-    top_right = 7
+    bottom_left = "bottom_left"
+    bottom_center = "bottom_center"
+    bottom_right = "bottom_right"
+    middle_left = "middle_left"
+    middle_center = "middle_center"
+    middle_right = "middle_right"
+    top_left = "top_left"
+    top_center = "top_center"
+    top_right = "top_right"
 
 
 class CaptionAnimation(str, Enum):
     """Caption animation properties for caption assets."""
 
-    float_in_bottom = "float_in_bottom"
+    # float_in_bottom = "float_in_bottom"
     box_highlight = "box_highlight"
     color_highlight = "color_highlight"
     reveal = "reveal"
@@ -424,8 +424,8 @@ def __init__(
         italic: bool = False,
         underline: bool = False,
         strikeout: bool = False,
-        scale_x: float = 1.0,
-        scale_y: float = 1.0,
+        scale_x: float = 100,
+        scale_y: float = 100,
         spacing: float = 0.0,
         angle: float = 0.0,
     ):

From 92dc137f82cb1969b1c76fa31bf6142ab4291dcf Mon Sep 17 00:00:00 2001
From: Ankit raj <113342181+ankit-v2-3@users.noreply.github.com>
Date: Tue, 5 Aug 2025 12:47:11 +0530
Subject: [PATCH 19/19] fix: border style

---
 videodb/timeline_v2.py | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/videodb/timeline_v2.py b/videodb/timeline_v2.py
index 925d755..efd560d 100644
--- a/videodb/timeline_v2.py
+++ b/videodb/timeline_v2.py
@@ -66,8 +66,7 @@ class HorizontalAlignment(str, Enum):
 class CaptionBorderStyle(str, Enum):
     """Border style properties for caption assets."""
 
-    no_border = "no_border"
-    opaque_box = "opaque_box"
+    outline_and_shadow = "outline_and_shadow"
     outline = "outline"
 
 
@@ -460,7 +459,7 @@ class BorderAndShadow:
 
     def __init__(
         self,
-        style: CaptionBorderStyle = CaptionBorderStyle.no_border,
+        style: CaptionBorderStyle = CaptionBorderStyle.outline_and_shadow,
         outline: int = 1,
         outline_color: str = "&H00000000",
         shadow: int = 0,