deepgeek/gradio-webrtc
2
0
Fork 0
mirror of https://github.com/HumanAIGC-Engineering/gradio-webrtc.git synced 2026-02-05 01:49:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add ability to Hide Title in Built-in UI + llama 4 cartesia tweaks (#299)

Browse Source 
* merge title

* Fix
This commit is contained in:
Freddy Boulton
2025-04-23 16:01:54 -04:00
committed by GitHub
parent 745701c79c
commit 02aef9da58
6 changed files with 131 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
backend/fastrtc/__init__.py
View File

@@ -17,7 +17,11 @@ from .reply_on_pause import AlgoOptions, ReplyOnPause
from .reply_on_stopwords import ReplyOnStopWords
from .speech_to_text import MoonshineSTT, get_stt_model
from .stream import Stream, UIArgs
from .text_to_speech import KokoroTTSOptions, get_tts_model
from .text_to_speech import (
CartesiaTTSOptions,
KokoroTTSOptions,
get_tts_model,
)
from .tracks import (
AsyncAudioVideoStreamHandler,
AsyncStreamHandler,
@@ -87,4 +91,5 @@ __all__ = [
"VideoStreamHandler",
"CloseStream",
"get_current_context",
"CartesiaTTSOptions",
]

164
backend/fastrtc/stream.py
View File

@@ -59,6 +59,8 @@ class UIArgs(TypedDict):
If "submit", the input will be sent when the submit event is triggered by the user.
If "change", the input will be sent whenever the user changes the input value.
"""
hide_title: NotRequired[bool]
"""If True, the title and subtitle will not be displayed."""
class Stream(WebRTCConnectionMixin):
@@ -339,21 +341,22 @@ class Stream(WebRTCConnectionMixin):
same_components.append(component)
if self.modality == "video" and self.mode == "receive":
with gr.Blocks() as demo:
gr.HTML(
f"""
<h1 style='text-align: center'>
{ui_args.get("title", "Video Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
if not ui_args.get("hide_title"):
gr.HTML(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
<h1 style='text-align: center'>
{ui_args.get("title", "Video Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
)
with gr.Row():
with gr.Column():
if additional_input_components:
@@ -391,21 +394,22 @@ class Stream(WebRTCConnectionMixin):
)
elif self.modality == "video" and self.mode == "send":
with gr.Blocks() as demo:
gr.HTML(
f"""
<h1 style='text-align: center'>
{ui_args.get("title", "Video Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
if not ui_args.get("hide_title"):
gr.HTML(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
<h1 style='text-align: center'>
{ui_args.get("title", "Video Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
)
with gr.Row():
if additional_input_components:
with gr.Column():
@@ -494,21 +498,22 @@ class Stream(WebRTCConnectionMixin):
)
elif self.modality == "audio" and self.mode == "receive":
with gr.Blocks() as demo:
gr.HTML(
f"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
if not ui_args.get("hide_title"):
gr.HTML(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
)
with gr.Row():
with gr.Column():
for component in additional_input_components:
@@ -549,21 +554,22 @@ class Stream(WebRTCConnectionMixin):
)
elif self.modality == "audio" and self.mode == "send":
with gr.Blocks() as demo:
gr.HTML(
f"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
if not ui_args.get("hide_title"):
gr.HTML(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
)
with gr.Row():
with gr.Column():
with gr.Group():
@@ -604,21 +610,22 @@ class Stream(WebRTCConnectionMixin):
)
elif self.modality == "audio" and self.mode == "send-receive":
with gr.Blocks() as demo:
gr.HTML(
f"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
if not ui_args.get("hide_title"):
gr.HTML(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
)
with gr.Row():
with gr.Column():
with gr.Group():
@@ -662,21 +669,22 @@ class Stream(WebRTCConnectionMixin):
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks(css=css) as demo:
gr.HTML(
f"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Video Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
if not ui_args.get("hide_title"):
gr.HTML(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
<h1 style='text-align: center'>
{ui_args.get("title", "Audio Video Streaming (Powered by FastRTC ⚡️)")}
</h1>
"""
)
if ui_args.get("subtitle"):
gr.Markdown(
f"""
<div style='text-align: center'>
{ui_args.get("subtitle")}
</div>
"""
)
with gr.Row():
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):

8
backend/fastrtc/text_to_speech/__init__.py
View File

@@ -1,3 +1,7 @@
from .tts import KokoroTTSOptions, get_tts_model
from .tts import (
CartesiaTTSOptions,
KokoroTTSOptions,
get_tts_model,
)
__all__ = ["get_tts_model", "KokoroTTSOptions"]
__all__ = ["get_tts_model", "KokoroTTSOptions", "CartesiaTTSOptions"]

5
backend/fastrtc/text_to_speech/tts.py
View File

@@ -2,7 +2,7 @@ import asyncio
import importlib.util
import re
from collections.abc import AsyncGenerator, Generator
from dataclasses import dataclass
from dataclasses import dataclass, field
from functools import lru_cache
from typing import Literal, Protocol, TypeVar
@@ -153,10 +153,11 @@ class KokoroTTSModel(TTSModel):
break
@dataclass
class CartesiaTTSOptions(TTSOptions):
voice: str = "71a7ad14-091c-4e8e-a314-022ece01c121"
language: str = "en"
emotion: list[str] = []
emotion: list[str] = field(default_factory=list)
cartesia_version: str = "2024-06-10"
model: str = "sonic-2"
sample_rate: int = 22_050