Skip to content

Update Phonic languages fields #5285

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

Open
qionghuang6 wants to merge 2 commits into
base: main
Choose a base branch
from
+34 −6
Open

Update Phonic languages fields #5285

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aa2fad9
update languages field
qionghuang6 Mar 31, 2026
2f5778a
backwards compat
qionghuang6 Mar 31, 2026
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
4 changes: 3 additions & 1 deletion livekit-plugins/livekit-plugins-phonic/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,9 @@ Set the `PHONIC_API_KEY` environment variable, or pass `api_key` directly to `Re
| `welcome_message` | `str` | Message the agent says when the conversation starts. Ignored when `generate_welcome_message` is True |
| `generate_welcome_message` | `bool` | Auto-generate the welcome message (ignores `welcome_message`) |
| `project` | `str` | Project name (default: `main`) |
| `languages` | `list[str]` | ISO 639-1 language codes the agent should recognize and speak |
| `default_language` | `str` | ISO 639-1 default language for recognition and speech |
| `additional_languages` | `list[str]` | Further ISO 639-1 codes (must not repeat `default_language`) |
| `multilingual_mode` | `"auto"` \| `"request"` | Per-utterance language detection vs. change on user request (recommended: `request`) |
| `audio_speed` | `float` | Audio playback speed |
| `phonic_tools` | `list[str]` | [Phonic Webhook tool](https://docs.phonic.co/docs/using-tools/tools_overview#webhook-tools) names available to the assistant |
| `boosted_keywords` | `list[str]` | Keywords to boost in speech recognition |
Expand Down
22 changes: 17 additions & 5 deletions livekit-plugins/livekit-plugins-phonic/livekit/plugins/phonic/realtime/realtime_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,9 @@ class _RealtimeOptions:
welcome_message: NotGivenOr[str | None]
generate_welcome_message: NotGivenOr[bool | None]
project: NotGivenOr[str | None]
languages: NotGivenOr[list[str]]
default_language: NotGivenOr[str]
additional_languages: NotGivenOr[list[str]]
multilingual_mode: NotGivenOr[Literal["auto", "request"]]
audio_speed: NotGivenOr[float]
phonic_tools: NotGivenOr[list[str]]
boosted_keywords: NotGivenOr[list[str]]
Expand Down Expand Up @@ -100,7 +102,9 @@ def __init__(
welcome_message: NotGivenOr[str | None] = NOT_GIVEN,
generate_welcome_message: NotGivenOr[bool] = NOT_GIVEN,
project: NotGivenOr[str | None] = NOT_GIVEN,
languages: NotGivenOr[list[str]] = NOT_GIVEN,
Copy link
Copy Markdown
Member

@davidzhao davidzhao Mar 31, 2026

Choose a reason for hiding this comment

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

same question re: backwards compatibility on patch versions

Copy link
Copy Markdown
Contributor Author

@qionghuang6 qionghuang6 Mar 31, 2026

Choose a reason for hiding this comment

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

Yup, let me update that.

default_language: NotGivenOr[str] = NOT_GIVEN,
additional_languages: NotGivenOr[list[str]] = NOT_GIVEN,
multilingual_mode: NotGivenOr[Literal["auto", "request"]] = NOT_GIVEN,
audio_speed: NotGivenOr[float] = NOT_GIVEN,
phonic_tools: NotGivenOr[list[str]] = NOT_GIVEN,
boosted_keywords: NotGivenOr[list[str]] = NOT_GIVEN,
Expand All @@ -123,7 +127,11 @@ def __init__(
generate_welcome_message: When True, the welcome message is automatically generated
and ``welcome_message`` is ignored.
project: Project name to use for the conversation.
languages: ISO 639-1 language codes the agent should recognize and speak.
default_language: ISO 639-1 default language for recognition and speech.
additional_languages: Further ISO 639-1 codes the agent may use (must not include
``default_language``).
multilingual_mode: ``\"auto\"`` to detect language per utterance, ``\"request\"`` to
switch only when the user asks (recommended).
audio_speed: Audio playback speed multiplier.
phonic_tools: Phonic tool names available to the assistant.
boosted_keywords: Keywords to boost in speech recognition.
Expand Down Expand Up @@ -159,7 +167,9 @@ def __init__(
welcome_message=welcome_message,
generate_welcome_message=generate_welcome_message,
project=project,
languages=languages,
default_language=default_language,
additional_languages=additional_languages,
multilingual_mode=multilingual_mode,
audio_speed=audio_speed,
phonic_tools=phonic_tools,
boosted_keywords=boosted_keywords,
Expand Down Expand Up @@ -491,7 +501,9 @@ async def _main_task(self) -> None:
"voice_id": self._opts.voice,
"input_format": "pcm_44100",
"output_format": "pcm_44100",
"recognized_languages": self._opts.languages,
"default_language": self._opts.default_language,
"additional_languages": self._opts.additional_languages,
"multilingual_mode": self._opts.multilingual_mode,
"audio_speed": self._opts.audio_speed,
"tools": tools_payload if len(tools_payload) > 0 else NOT_GIVEN,
"boosted_keywords": self._opts.boosted_keywords,
Expand Down
2 changes: 1 addition & 1 deletion livekit-plugins/livekit-plugins-phonic/pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ dependencies = [
"livekit-agents>=1.5.1",
"websockets>=11.0",
"aiohttp>=3.8.0",
"phonic>=0.31.5"
"phonic>=0.31.8"
]

[project.urls]
Expand Down
Loading