Simplismart Integration in Livekit

livekit-plugins/livekit-plugins-simplismart/README.md

@@ -0,0 +1,18 @@
+# Simplismart Plugin for LiveKit Agents
+
+Support for [Simplismart.ai](https://simplismart.ai)'s voice AI services in LiveKit Agents.
+
+## Features
+
+- **Speech-to-Text (STT)**: Convert audio to text using Simplismart's STT models. See the [STT docs](https://docs.livekit.io/agents/integrations/stt/simplismart/) for more information.
+- **Text-to-Speech (TTS)**: Convert text to audio using Simplismart's TTS models. See the [TTS docs](https://docs.livekit.io/agents/integrations/tts/simplismart/) for more information.
+
+## Installation 
+
+```bash
+pip install livekit-plugins-simplismart
+```
+
+## Pre-requisites
+
+You'll need an API key from Simplismart.ai. It can be set as an environment variable: `SIMPLISMART_API_KEY` 

livekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/__init__.py

@@ -0,0 +1,50 @@
+# Copyright 2025 LiveKit, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""SimpliSmart plugin for LiveKit Agents
+
+Support for speech-to-text and text-to-speech with [SimpliSmart](https://simplismart.ai/).
+
+SimpliSmart provides high-quality STT and TTS for Indian languages.
+
+For API access, visit https://simplismart.ai/
+"""
+
+from .stt import STT
+from .tts import TTS
+from .version import __version__
+
+__all__ = ["STT", "TTS", "__version__"]
+
+
+from livekit.agents import Plugin
+
+from .log import logger
+
+
+class SimplismartPlugin(Plugin):
+    def __init__(self) -> None:
+        super().__init__(__name__, __version__, __package__, logger)
+
+
+Plugin.register_plugin(SimplismartPlugin())
+
+# Cleanup docs of unexported modules
+_module = dir()
+NOT_IN_ALL = [m for m in _module if m not in __all__]
+
+__pdoc__ = {}
+
+for n in NOT_IN_ALL:
+    __pdoc__[n] = False

livekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/log.py

@@ -0,0 +1,3 @@
+import logging
+
+logger = logging.getLogger("livekit.plugins.simplismart")

livekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/stt.py

@@ -0,0 +1,183 @@
+# Copyright 2025 LiveKit, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Speech-to-Text implementation for SimpliSmart
+
+This module provides an STT implementation that uses the SimpliSmart API.
+"""
+
+import asyncio
+import base64
+import os
+from typing import Any, Literal
+
+import aiohttp
+from pydantic import BaseModel
+
+from livekit.agents import (
+    APIConnectionError,
+    APIConnectOptions,
+    APIStatusError,
+    APITimeoutError,
+    stt,
+    utils,
+)
+from livekit.agents.types import DEFAULT_API_CONNECT_OPTIONS, NOT_GIVEN, NotGivenOr
+from livekit.agents.utils import AudioBuffer, rtc
+
+from .log import logger
+
+
+class SimplismartSTTOptions(BaseModel):
+    language: str | None = None
+    task: Literal["transcribe", "translate"] = "transcribe"
+    without_timestamps: bool = True
+    vad_model: Literal["silero", "frame"] = "frame"
+    vad_filter: bool = True
+    model: str | None = "openai/whisper-large-v3-turbo"
+    word_timestamps: bool = False
+    vad_onset: float | None = 0.5
+    vad_offset: float | None = None
+    min_speech_duration_ms: int = 0
+    max_speech_duration_s: float = 30
+    min_silence_duration_ms: int = 2000
+    speech_pad_ms: int = 400
+    diarization: bool = False
+    initial_prompt: str | None = None
+    hotwords: str | None = None
+    num_speakers: int = 0
+    compression_ratio_threshold: float | None = 2.4
+    beam_size: int = 4
+    temperature: float = 0.0
+    multilingual: bool = False
+    max_tokens: float | None = 400
+    log_prob_threshold: float | None = -1.0
+    length_penalty: int = 1
+    repetition_penalty: float = 1.01
+    suppress_tokens: list[int] = [-1]
+    strict_hallucination_reduction: bool = False
+
+
+class STT(stt.STT):
+    def __init__(
+        self,
+        *,
+        base_url: str,
+        api_key: str | None = None,
+        model: str | None = None,
+        params: dict[str, Any] | SimplismartSTTOptions | None = None,
+        http_session: aiohttp.ClientSession | None = None,
+    ):
+        super().__init__(
+            capabilities=stt.STTCapabilities(
+                streaming=False,
+                interim_results=False,
+                aligned_transcript="word",
+            )
+        )
+
+        self._api_key = api_key or os.environ.get("SIMPLISMART_API_KEY")
+        if not self._api_key:
+            raise ValueError("SIMPLISMART_API_KEY is not set")
+
+        if params is None:
+            params = SimplismartSTTOptions()
+
+        if isinstance(params, SimplismartSTTOptions):
+            self._opts = params
+            self._model = params.model
+        else:
+            self._opts = SimplismartSTTOptions(**params)
+
+        self._base_url = base_url
+        self._logger = logger.getChild(self.__class__.__name__)
+        self._session = http_session
+
+
+    @property
+    def provider(self) -> str:
+        return "Simplismart"
+
+    def _ensure_session(self) -> aiohttp.ClientSession:
+        if not self._session:
+            self._session = utils.http_context.http_session()
+        return self._session
+
+    async def _recognize_impl(
+        self,
+        buffer: AudioBuffer,
+        *,
+        language: NotGivenOr[str] = NOT_GIVEN,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
+    ) -> stt.SpeechEvent:
+        language = self._opts.language if isinstance(language, type(NOT_GIVEN)) else language
+        wav_bytes = rtc.combine_audio_frames(buffer).to_wav_bytes()
+
+        audio_b64 = base64.b64encode(wav_bytes).decode("utf-8")
+        payload = self._opts.model_dump()
+
+        payload["audio_data"] = audio_b64
+        payload["language"] = language
+        payload["model"] = self._model
+
+        try:
+            async with self._ensure_session().post(
+                self._base_url,
+                json=payload,
+                headers={
+                    "Authorization": f"Bearer {self._api_key}",
+                    "Content-Type": "application/json",
+                },
+            ) as res:
+                if res.status != 200:
+                    error_text = await res.text()
+                    self._logger.error(f"Simplismart API error: {res.status} - {error_text}")
+                    raise APIStatusError(
+                        message=f"Simplismart API Error: {error_text}",
+                        status_code=res.status,
+                    )
+
+                response_json = await res.json()
+
+                detected_language = response_json["info"]["language"]
+
+                start_time = response_json["timestamps"][0][0]
+                end_time = response_json["timestamps"][-1][1]
+                request_id = response_json.get("request_id", "")
+                text = "".join(response_json["transcription"])
+
+                alternatives = [
+                    stt.SpeechData(
+                        language=detected_language,
+                        text=text,
+                        start_time=start_time,
+                        end_time=end_time,
+                        confidence=1.0,
+                    ),
+                ]
+
+                return stt.SpeechEvent(
+                    type=stt.SpeechEventType.FINAL_TRANSCRIPT,
+                    request_id=request_id,
+                    alternatives=alternatives,
+                )
+        except asyncio.TimeoutError as e:
+            self._logger.error(f"Simplismart API timeout: {e}")
+            raise APITimeoutError("Simplismart API request timed out") from e
+        except aiohttp.ClientError as e:
+            self._logger.error(f"Simplismart API client error: {e}")
+            raise APIConnectionError(f"Simplismart API connection error: {e}") from e
+        except Exception as e:
+            self._logger.error(f"Error during Simplismart STT processing: {e}")
+            raise APIConnectionError(f"Unexpected error in Simplismart STT: {e}") from e

livekit-plugins/livekit-plugins-simplismart/livekit/plugins/simplismart/tts.py

@@ -0,0 +1,129 @@
+import asyncio
+import os
+from typing import Any
+
+import aiohttp
+
+# from .log import logger
+from pydantic import BaseModel
+
+from livekit.agents import (
+    DEFAULT_API_CONNECT_OPTIONS,
+    APIConnectionError,
+    APIConnectOptions,
+    APIStatusError,
+    APITimeoutError,
+    tts,
+    utils,
+)
+
+
+class SimplismartTTSOptions(BaseModel):
+    temperature: float = 0.7
+    top_p: float = 0.9
+    repetition_penalty: float = 1.5
+    max_tokens: int = 1000
+
+
+class TTS(tts.TTS):
+    def __init__(
+        self,
+        *,
+        base_url: str,
+        model: str | None = "Simplismart/orpheus-3b-0.1-ft",
+        voice="tara",
+        api_key: str | None = None,
+        params: dict[str, Any] | SimplismartTTSOptions | None = None,
+        http_session: aiohttp.ClientSession | None = None,
+        **kwargs: Any,
+    ) -> None:
+        super().__init__(
+            capabilities=tts.TTSCapabilities(streaming=False),
+            sample_rate=24000,
+            num_channels=1,
+        )
+
+        self._base_url = base_url
+        self._model = model
+        self._voice = voice
+        self._api_key = api_key or os.environ.get("SIMPLISMART_API_KEY")
+        if not self._api_key:
+            raise ValueError("SIMPLISMART_API_KEY is not set")
+
+        self._session = http_session
+
+        if params is None:
+            params = SimplismartTTSOptions()
+
+        if isinstance(params, SimplismartTTSOptions):
+            self._opts = params
+        else:
+            self._opts = SimplismartTTSOptions(**params)
+
+    @property
+    def model(self) -> str:
+        return self._model
+
+    @property
+    def provider(self) -> str:
+        return "SimpliSmart"
+
+    def _ensure_session(self) -> aiohttp.ClientSession:
+        if not self._session:
+            self._session = utils.http_context.http_session()
+        return self._session
+
+    def synthesize(
+        self,
+        text: str,
+        *,
+        conn_options: APIConnectOptions = DEFAULT_API_CONNECT_OPTIONS,
+    ) -> "ChunkedStream":
+        return ChunkedStream(tts=self, input_text=text, conn_options=conn_options)
+
+
+class ChunkedStream(tts.ChunkedStream):
+    def __init__(self, *, tts: TTS, input_text: str, conn_options: APIConnectOptions) -> None:
+        super().__init__(tts=tts, input_text=input_text, conn_options=conn_options)
+        self._tts: TTS = tts
+        self._opts = tts._opts
+        self._model = tts._model
+
+    async def _run(self, output_emitter: tts.AudioEmitter) -> None:
+        payload = self._opts.model_dump()
+        payload["prompt"] = self._input_text
+        payload["voice"] = self._tts._voice
+        payload["model"] = "Simplismart/orpheus-3b-0.1-ft"
+
+        headers = {
+            "Authorization": f"Bearer {self._tts._api_key}",
+            "Content-Type": "application/json",
+        }
+
+        try:
+            async with self._tts._ensure_session().post(
+                self._tts._base_url,
+                json=payload,
+                headers=headers,
+                timeout=aiohttp.ClientTimeout(
+                    total=self._conn_options.timeout,
+                    sock_connect=self._conn_options.timeout,
+                ),
+            ) as resp:
+                resp.raise_for_status()
+                output_emitter.initialize(
+                    request_id=utils.shortuuid(),
+                    sample_rate=self._tts.sample_rate,
+                    num_channels=self._tts.num_channels,
+                    mime_type="audio/pcm",
+                )
+                async for audio_data, _ in resp.content.iter_chunks():
+                    output_emitter.push(audio_data)
+        except asyncio.TimeoutError:
+            raise APITimeoutError() from None
+        except aiohttp.ClientResponseError as e:
+            raise APIStatusError(
+                message=e.message, status_code=e.status, request_id=None, body=None
+            ) from None
+        except Exception as e:
+            raise APIConnectionError() from e