Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Personas config and tts options #125

Merged
merged 2 commits into from
Apr 3, 2024
Merged

Personas config and tts options #125

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1eb7339
personas config and tts config passed through
williamluer Apr 3, 2024
0df17ee
cleanup
williamluer Apr 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions openduck-py/openduck_py/response_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -496,9 +496,13 @@ async def speak_response(
response_text, voice_id=self.tts_config.voice_id
)
elif self.tts_config.provider == "openai":
audio_bytes_iter = aio_openai_tts(response_text)
audio_bytes_iter = aio_openai_tts(
response_text, voice=self.tts_config.voice_id
)
elif self.tts_config.provider == "azure":
audio_bytes_iter = aio_azure_tts(response_text)
audio_bytes_iter = aio_azure_tts(
response_text, voice_name=self.tts_config.voice_id
)
elif self.tts_config.provider == "gptsovits":
audio_bytes_iter = aio_gptsovits_tts(
response_text, voice_ref=self.tts_config.voice_id
Expand Down
46 changes: 36 additions & 10 deletions openduck-py/openduck_py/routers/voice.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,30 @@
).content
)

personas = {
"podcast": {
"voice": ELEVENLABS_VIKRAM,
"voice_provider": "elevenlabs",
"username": "Vikram (AI)",
"prompt": "podcast.txt",
"speak_first": True,
},
"comedy": {
"voice": "alloy",
"voice_provider": "openai",
"username": "Emily (AI)",
"prompt": "comedy.txt",
"speak_first": True,
},
"todo": {
"voice": "onyx",
"voice_provider": "openai",
"username": "Alex (AI)",
"prompt": "todo.txt",
"speak_first": True,
},
}

audio_router = APIRouter(prefix="/audio")

Daily.init()
Expand Down Expand Up @@ -126,10 +150,13 @@ async def create_room_and_start(request: StartCallRequest):
target=run_connect_daily,
kwargs=dict(
room_url=room_info["url"],
username="Vikram (AI)",
prompt=f"{request.prompt}.txt",
voice_id=ELEVENLABS_VIKRAM,
speak_first=True,
username=personas[request.prompt]["username"],
prompt=personas[request.prompt]["prompt"],
tts_config=TTSConfig(
provider=personas[request.prompt]["voice_provider"],
voice_id=personas[request.prompt]["voice"],
),
speak_first=personas[request.prompt]["speak_first"],
context=context,
room_id=room_info["id"],
),
Comment on lines 151 to 162
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
kwargs=dict(
room_url=room_info["url"],
username="Vikram (AI)",
prompt=f"{request.prompt}.txt",
voice_id=ELEVENLABS_VIKRAM,
speak_first=True,
username=personas[request.prompt]["username"],
prompt=personas[request.prompt]["prompt"],
tts_config=TTSConfig(
provider=personas[request.prompt]["voice_provider"],
voice_id=personas[request.prompt]["voice"],
),
speak_first=personas[request.prompt]["speak_first"],
context=context,
room_id=room_info["id"],
),
kwargs={
room_url=room_info["url"],
username=personas[request.prompt]["username"],
prompt=personas[request.prompt]["prompt"],
tts_config=TTSConfig(
provider=personas[request.prompt]["voice_provider"],
voice_id=personas[request.prompt]["voice"],
),
speak_first=personas[request.prompt]["speak_first"],
context=context,
room_id=room_info["id"],
},

Expand Down Expand Up @@ -230,7 +257,7 @@ async def connect_daily(
room="https://matthewkennedy5.daily.co/Od7ecHzUW4knP6hS5bug",
username: str = "host (AI)",
system_prompt="system-prompt",
voice_id: str = None,
tts_config: TTSConfig = None,
speak_first: bool = False,
context: Optional[Dict[str, str]] = None,
record: bool = True,
Expand Down Expand Up @@ -280,13 +307,12 @@ async def connect_daily(
}
if context is not None:
base_context.update(context)

responder = ResponseAgent(
session_id=session_id,
record=record,
input_audio_format="int16",
tts_config=TTSConfig(provider="openai"),
# tts_config=TTSConfig(provider="elevenlabs", voice_id=voice_id),
# tts_config=TTSConfig(provider="azure"),
tts_config=tts_config,
system_prompt=system_prompt,
context=base_context,
)
Expand Down Expand Up @@ -359,7 +385,7 @@ def run_connect_daily(
room_url: str,
username: str,
prompt: str,
voice_id: Optional[str] = None,
tts_config: Optional[TTSConfig] = None,
speak_first: bool = False,
context: Optional[Dict[str, str]] = None,
room_id: str = None,
Expand All @@ -369,7 +395,7 @@ def run_connect_daily(
room=room_url,
username=username,
system_prompt=prompt,
voice_id=voice_id,
tts_config=tts_config,
speak_first=speak_first,
context=context,
room_id=room_id,
Expand Down
Loading