mirror of
https://github.com/dograh-hq/dograh.git
synced 2026-06-22 08:38:13 +02:00
085ab0a7ae
Telnyx's bidirectional stream uses different codecs per direction:
- Dograh → Telnyx: what we declare via `stream_bidirectional_codec`
- Telnyx → Dograh: whatever the PSTN leg negotiated (PCMA for UK,
Europe, India termination; PCMU for US), announced as
`media_format.encoding` on the WebSocket start message.
We hardcoded both directions on the serializer to PCMU, so any call
whose PSTN leg used PCMA arrived as A-law bytes that we decoded
through a μ-law table → static for the entire call.
`handle_websocket` now extracts `media_format.encoding` from the
start message and threads it through `transport_kwargs`. The
serializer uses it for the Telnyx → Dograh direction; the
Dograh → Telnyx direction stays pinned to PCMU to match the
unchanged `stream_bidirectional_codec` in the dial/answer payloads.
Note: pipecat's `TelnyxFrameSerializer` names its params from the
call's POV, not Dograh's — `inbound_encoding` is what we send into
the call, `outbound_encoding` is what we receive. Easy to mix up.
66 lines
2.2 KiB
Python
66 lines
2.2 KiB
Python
"""Telnyx transport factory."""
|
|
|
|
from fastapi import WebSocket
|
|
|
|
from api.services.pipecat.audio_config import AudioConfig
|
|
from api.services.pipecat.audio_mixer import build_audio_out_mixer
|
|
from api.services.telephony.factory import load_credentials_for_transport
|
|
from pipecat.transports.websocket.fastapi import (
|
|
FastAPIWebsocketParams,
|
|
FastAPIWebsocketTransport,
|
|
)
|
|
|
|
from .serializers import TelnyxFrameSerializer
|
|
|
|
|
|
async def create_transport(
|
|
websocket: WebSocket,
|
|
workflow_run_id: int,
|
|
audio_config: AudioConfig,
|
|
organization_id: int,
|
|
*,
|
|
vad_config: dict | None = None,
|
|
ambient_noise_config: dict | None = None,
|
|
telephony_configuration_id: int | None = None,
|
|
stream_id: str,
|
|
call_control_id: str,
|
|
encoding: str = "PCMU",
|
|
):
|
|
"""Create a transport for Telnyx connections."""
|
|
config = await load_credentials_for_transport(
|
|
organization_id, telephony_configuration_id, expected_provider="telnyx"
|
|
)
|
|
|
|
api_key = config.get("api_key")
|
|
if not api_key:
|
|
raise ValueError(
|
|
f"Incomplete Telnyx configuration for organization {organization_id}"
|
|
)
|
|
|
|
# Pipecat's TelnyxFrameSerializer names its params from the call's POV,
|
|
# not Dograh's: ``inbound_encoding`` is what we *send into the call*
|
|
# (Dograh → Telnyx), and ``outbound_encoding`` is what we *receive out of
|
|
# the call* (Telnyx → Dograh).
|
|
serializer = TelnyxFrameSerializer(
|
|
stream_id=stream_id,
|
|
call_control_id=call_control_id,
|
|
api_key=api_key,
|
|
inbound_encoding="PCMU", # Dograh → Telnyx; matches stream_bidirectional_codec
|
|
outbound_encoding=encoding, # Telnyx → Dograh; from media_format.encoding
|
|
)
|
|
|
|
mixer = await build_audio_out_mixer(
|
|
audio_config.transport_out_sample_rate, ambient_noise_config
|
|
)
|
|
|
|
return FastAPIWebsocketTransport(
|
|
websocket=websocket,
|
|
params=FastAPIWebsocketParams(
|
|
audio_in_enabled=True,
|
|
audio_out_enabled=True,
|
|
audio_in_sample_rate=audio_config.transport_in_sample_rate,
|
|
audio_out_sample_rate=audio_config.transport_out_sample_rate,
|
|
audio_out_mixer=mixer,
|
|
serializer=serializer,
|
|
),
|
|
)
|