feat: split USB/Network mode into separate USB and AES67 input options with dedicated device lists

This commit is contained in:
2025-09-08 14:02:36 +02:00
parent 26cd6d5c56
commit e80ff79d67
3 changed files with 147 additions and 57 deletions
+42 -15
View File
@@ -37,16 +37,23 @@ except Exception:
st.title("🎙️ Auracast Audio Mode Control")
# Audio mode selection with persisted default
options = ["Webapp", "USB/Network", "Demo"]
# Note: backend persists 'USB' for any device:<name> source (including AES67). We default to 'USB' in that case.
options = ["Webapp", "USB", "AES67", "Demo"]
saved_audio_mode = saved_settings.get("audio_mode", "Webapp")
if saved_audio_mode not in options:
saved_audio_mode = "Webapp"
# Map legacy/unknown modes to closest
mapping = {"USB/Network": "USB", "Network": "AES67"}
saved_audio_mode = mapping.get(saved_audio_mode, "Webapp")
audio_mode = st.selectbox(
"Audio Mode",
options,
index=options.index(saved_audio_mode),
help="Select the audio input source. Choose 'Webapp' for browser microphone, 'USB/Network' for a connected hardware device, or 'Demo' for a simulated stream."
index=options.index(saved_audio_mode) if saved_audio_mode in options else options.index("Webapp"),
help=(
"Select the audio input source. Choose 'Webapp' for browser microphone, "
"'USB' for a connected USB audio device (via PipeWire), 'AES67' for network RTP/AES67 sources, "
"or 'Demo' for a simulated stream."
)
)
if audio_mode == "Demo":
@@ -200,16 +207,22 @@ else:
else:
mic_gain = 1.0
# Input device selection for USB mode
if audio_mode == "USB/Network":
resp = requests.get(f"{BACKEND_URL}/audio_inputs")
device_list = resp.json().get('inputs', [])
# Input device selection for USB or AES67 mode
if audio_mode in ("USB", "AES67"):
try:
endpoint = "/audio_inputs_pw_usb" if audio_mode == "USB" else "/audio_inputs_pw_network"
resp = requests.get(f"{BACKEND_URL}{endpoint}")
device_list = resp.json().get('inputs', [])
except Exception as e:
st.error(f"Failed to fetch devices: {e}")
device_list = []
# Display "name [id]" but use name as value
input_options = [f"{d['name']} [{d['id']}]" for d in device_list]
option_name_map = {f"{d['name']} [{d['id']}]": d['name'] for d in device_list}
device_names = [d['name'] for d in device_list]
# Determine default input by name
# Determine default input by name (from persisted server state)
default_input_name = saved_settings.get('input_device')
if default_input_name not in device_names and device_names:
default_input_name = device_names[0]
@@ -219,10 +232,20 @@ else:
default_input_label = label
break
if not input_options:
st.warning("No hardware audio input devices found. Plug in a USB input device and click Refresh.")
warn_text = (
"No USB audio input devices found. Connect a USB input and click Refresh."
if audio_mode == "USB" else
"No AES67/Network inputs found. Ensure AES67 sources are visible in PipeWire and click Refresh."
)
st.warning(warn_text)
if st.button("Refresh"):
# For completeness, refresh the general audio cache as well
try:
requests.post(f"{BACKEND_URL}/refresh_audio_inputs", timeout=3)
r = requests.post(f"{BACKEND_URL}/refresh_audio_inputs", json={"force": True}, timeout=5)
if r.ok:
jr = r.json()
if jr.get('stopped_stream'):
st.info("An active stream was stopped to perform a full device refresh.")
except Exception as e:
st.error(f"Failed to refresh devices: {e}")
st.rerun()
@@ -238,12 +261,16 @@ else:
with col2:
if st.button("Refresh"):
try:
requests.post(f"{BACKEND_URL}/refresh_audio_inputs", timeout=3)
r = requests.post(f"{BACKEND_URL}/refresh_audio_inputs", json={"force": True}, timeout=5)
if r.ok:
jr = r.json()
if jr.get('stopped_stream'):
st.info("An active stream was stopped to perform a full device refresh.")
except Exception as e:
st.error(f"Failed to refresh devices: {e}")
st.rerun()
# Send only the device name to backend
input_device = option_name_map[selected_option] if selected_option in option_name_map else None
input_device = option_name_map.get(selected_option)
else:
input_device = None
@@ -304,11 +331,11 @@ else:
program_info=program_info,
language=language,
audio_source=(
f"device:{input_device}" if audio_mode == "USB/Network" else (
f"device:{input_device}" if audio_mode in ("USB", "AES67") else (
"webrtc" if audio_mode == "Webapp" else "network"
)
),
input_format=(f"int16le,{q['rate']},1" if audio_mode == "USB/Network" else "auto"),
input_format=(f"int16le,{q['rate']},1" if audio_mode in ("USB", "AES67") else "auto"),
iso_que_len=1,
sampling_frequency=q['rate'],
octets_per_frame=q['octets'],
+88 -38
View File
@@ -15,23 +15,33 @@ from aiortc import RTCPeerConnection, RTCSessionDescription, MediaStreamTrack
import av
import av.audio.layout
import sounddevice as sd # type: ignore
from typing import Set, List, Dict, Any
from typing import Set
import traceback
from auracast.utils.sounddevice_utils import (
list_usb_pw_inputs,
list_network_pw_inputs,
)
PTIME = 40 # TODO: seems to have no effect at all
pcs: Set[RTCPeerConnection] = set() # keep refs so they dont GC early
AUDIO_INPUT_DEVICES_CACHE: List[Dict[str, Any]] = []
class Offer(BaseModel):
sdp: str
type: str
def get_device_index_by_name(name: str):
"""Return the device index for a given device name, or None if not found."""
for d in AUDIO_INPUT_DEVICES_CACHE:
if d["name"] == name:
return d["id"]
"""Return the device index for a given device name, or None if not found.
Queries the current sounddevice list directly (no cache).
"""
try:
devs = sd.query_devices()
for idx, d in enumerate(devs):
if d.get("name") == name and d.get("max_input_channels", 0) > 0:
return idx
except Exception:
pass
return None
@@ -232,47 +242,87 @@ async def get_status():
return status
async def scan_audio_devices():
"""Scans for available audio devices and updates the cache."""
global AUDIO_INPUT_DEVICES_CACHE
log.info("Scanning for audio input devices...")
@app.post("/refresh_audio_inputs")
async def refresh_audio_inputs(force: bool = False):
"""Triggers a re-scan of audio devices.
If force is True and a stream is active, the stream(s) will be stopped to allow
a full re-initialization of the sounddevice backend. The response will include
'stopped_stream': True if any running stream was stopped.
"""
stopped = False
if force:
try:
# Stop active streams before forcing sounddevice re-init
if multicaster1 is not None and multicaster1.get_status().get('is_streaming'):
await multicaster1.stop_streaming()
stopped = True
if multicaster2 is not None and multicaster2.get_status().get('is_streaming'):
await multicaster2.stop_streaming()
stopped = True
except Exception:
log.warning("Failed to stop stream(s) before force refresh", exc_info=True)
# Reinitialize sounddevice backend if requested
try:
if sys.platform == 'linux':
log.info("Re-initializing sounddevice to scan for new devices")
if sys.platform == 'linux' and force:
log.info("Force re-initializing sounddevice backend")
sd._terminate()
sd._initialize()
devs = sd.query_devices()
inputs = [
dict(d, id=idx)
for idx, d in enumerate(devs)
if d.get("max_input_channels", 0) > 0
]
log.info('Found %d audio input devices: %s', len(inputs), inputs)
AUDIO_INPUT_DEVICES_CACHE = inputs
except Exception:
log.error("Exception while scanning audio devices:", exc_info=True)
# Do not clear cache on error, keep the last known good list
log.error("Exception while force-refreshing audio devices:", exc_info=True)
return {"status": "ok", "inputs": [], "stopped_stream": stopped}
@app.on_event("startup")
async def startup_event():
"""Pre-scans audio devices on startup."""
await scan_audio_devices()
@app.get("/audio_inputs_pw_usb")
async def audio_inputs_pw_usb():
"""List PipeWire USB input nodes mapped to sounddevice indices.
Returns a list of dicts: [{id, name, max_input_channels}].
"""
try:
# Do not refresh PortAudio if we are currently streaming to avoid termination
streaming = False
try:
if multicaster1 is not None:
status = multicaster1.get_status()
streaming = bool(status.get('is_streaming'))
except Exception:
streaming = False
devices = [
{"id": idx, "name": dev.get("name"), "max_input_channels": dev.get("max_input_channels", 0)}
for idx, dev in list_usb_pw_inputs(refresh=not streaming)
]
return {"inputs": devices}
except Exception as e:
log.error("Exception in /audio_inputs_pw_usb: %s", traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@app.get("/audio_inputs")
async def list_audio_inputs():
"""Return available hardware audio input devices from cache (by name, for selection)."""
# Only expose name and id for frontend
return {"inputs": AUDIO_INPUT_DEVICES_CACHE}
@app.get("/audio_inputs_pw_network")
async def audio_inputs_pw_network():
"""List PipeWire Network/AES67 input nodes mapped to sounddevice indices.
@app.post("/refresh_audio_inputs")
async def refresh_audio_inputs():
"""Triggers a re-scan of audio devices."""
await scan_audio_devices()
return {"status": "ok", "inputs": AUDIO_INPUT_DEVICES_CACHE}
Returns a list of dicts: [{id, name, max_input_channels}].
"""
try:
# Do not refresh PortAudio if we are currently streaming to avoid termination
streaming = False
try:
if multicaster1 is not None:
status = multicaster1.get_status()
streaming = bool(status.get('is_streaming'))
except Exception:
streaming = False
devices = [
{"id": idx, "name": dev.get("name"), "max_input_channels": dev.get("max_input_channels", 0)}
for idx, dev in list_network_pw_inputs(refresh=not streaming)
]
return {"inputs": devices}
except Exception as e:
log.error("Exception in /audio_inputs_pw_network: %s", traceback.format_exc())
raise HTTPException(status_code=500, detail=str(e))
@app.post("/offer")
+17 -4
View File
@@ -42,17 +42,25 @@ def _sd_matches_from_names(pa_idx, names):
if d["hostapi"] != pa_idx or d["max_input_channels"] <= 0:
continue
dn = d["name"].lower()
# Exclude monitor devices (e.g., "Monitor of ...") to avoid false positives
if "monitor" in dn:
continue
if any(n in dn for n in names_l):
out.append((i, d))
return out
def list_usb_pw_inputs():
def list_usb_pw_inputs(refresh: bool = True):
"""
Return [(device_index, device_dict), ...] for PipeWire **input** nodes
backed by **USB** devices (excludes monitor sources).
Parameters:
- refresh (bool): If True (default), force PortAudio to re-enumerate devices
before mapping. Set to False to avoid disrupting active streams.
"""
# Refresh PortAudio so we see newly added nodes before mapping
_sd_refresh()
if refresh:
_sd_refresh()
pa_idx = _pa_like_hostapi_index()
pw = _pw_dump()
@@ -84,13 +92,18 @@ def list_usb_pw_inputs():
# Map to sounddevice devices on PipeWire host API
return _sd_matches_from_names(pa_idx, usb_input_names)
def list_network_pw_inputs():
def list_network_pw_inputs(refresh: bool = True):
"""
Return [(device_index, device_dict), ...] for PipeWire **input** nodes that
look like network/AES67/RTP sources (excludes monitor sources).
Parameters:
- refresh (bool): If True (default), force PortAudio to re-enumerate devices
before mapping. Set to False to avoid disrupting active streams.
"""
# Refresh PortAudio so we see newly added nodes before mapping
_sd_refresh()
if refresh:
_sd_refresh()
pa_idx = _pa_like_hostapi_index()
pw = _pw_dump()