Merge pull request #860 from pipecat-ai/mb/transcription

Add a TranscriptProcessor and new frames

CHANGELOG.md

@@ -21,7 +21,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
   `audioop-lts` (https://github.com/AbstractUmbra/audioop) to provide the same
   functionality.
 
-- Added support for more languages to ElevenLabs (Arabic, Croatian, Filipino,
+- Added timestamped conversation transcript support:
+
+  - New `TranscriptProcessor` factory provides access to user and assistant
+    transcript processors.
+  - `UserTranscriptProcessor` processes user speech with timestamps from
+    transcription.
+  - `AssistantTranscriptProcessor` processes assistant responses with LLM
+    context timestamps.
+  - Messages emitted with ISO 8601 timestamps indicating when they were spoken.
+  - Supports all LLM formats (OpenAI, Anthropic, Google) via standard message
+    format.
+  - New examples: `28a-transcription-processor-openai.py`,
+    `28b-transcription-processor-anthropic.py`, and
+    `28c-transcription-processor-gemini.py`.
+
+- Add support for more languages to ElevenLabs (Arabic, Croatian, Filipino,
   Tamil) and PlayHT (Afrikans, Albanian, Amharic, Arabic, Bengali, Croatian,
   Galician, Hebrew, Mandarin, Serbian, Tagalog, Urdu, Xhosa).
 

examples/foundational/28a-transcription-processor-openai.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+from typing import List
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.transcript_processor import TranscriptProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptHandler:
+    """Simple handler to demonstrate transcript processing.
+
+    Maintains a list of conversation messages and logs them with timestamps.
+    """
+
+    def __init__(self):
+        self.messages: List[TranscriptionMessage] = []
+
+    async def on_transcript_update(
+        self, processor: TranscriptProcessor, frame: TranscriptionUpdateFrame
+    ):
+        """Handle new transcript messages.
+
+        Args:
+            processor: The TranscriptProcessor that emitted the update
+            frame: TranscriptionUpdateFrame containing new messages
+        """
+        self.messages.extend(frame.messages)
+
+        # Log the new messages
+        logger.info("New transcript messages:")
+        for msg in frame.messages:
+            timestamp = f"[{msg.timestamp}] " if msg.timestamp else ""
+            logger.info(f"{timestamp}{msg.role}: {msg.content}")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = OpenAILLMService(
+            api_key=os.getenv("OPENAI_API_KEY"),
+            model="gpt-4o",
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative, helpful, and brief way. Say hello.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        # Create transcript processor and handler
+        transcript = TranscriptProcessor()
+        transcript_handler = TranscriptHandler()
+
+        # Register event handler for transcript updates
+        @transcript.event_handler("on_transcript_update")
+        async def on_transcript_update(processor, frame):
+            await transcript_handler.on_transcript_update(processor, frame)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                transcript.user(),  # User transcripts
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+                transcript.assistant(),  # Assistant transcripts
+            ]
+        )
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/28b-transcript-processor-anthropic.py

@@ -0,0 +1,137 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+from typing import List
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import TranscriptionMessage, TranscriptionUpdateFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.transcript_processor import TranscriptProcessor
+from pipecat.services.anthropic import AnthropicLLMService
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptHandler:
+    """Simple handler to demonstrate transcript processing.
+
+    Maintains a list of conversation messages and logs them with timestamps.
+    """
+
+    def __init__(self):
+        self.messages: List[TranscriptionMessage] = []
+
+    async def on_transcript_update(
+        self, processor: TranscriptProcessor, frame: TranscriptionUpdateFrame
+    ):
+        """Handle new transcript messages.
+
+        Args:
+            processor: The TranscriptProcessor that emitted the update
+            frame: TranscriptionUpdateFrame containing new messages
+        """
+        self.messages.extend(frame.messages)
+
+        # Log the new messages
+        logger.info("New transcript messages:")
+        for msg in frame.messages:
+            timestamp = f"[{msg.timestamp}] " if msg.timestamp else ""
+            logger.info(f"{timestamp}{msg.role}: {msg.content}")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = AnthropicLLMService(
+            api_key=os.getenv("ANTHROPIC_API_KEY"), model="claude-3-5-sonnet-20241022"
+        )
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative, helpful, and brief way.",
+            },
+            {"role": "user", "content": "Say hello."},
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        # Create transcript processor and handler
+        transcript = TranscriptProcessor()
+        transcript_handler = TranscriptHandler()
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                transcript.user(),  # User transcripts
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+                transcript.assistant(),  # Assistant transcripts
+            ]
+        )
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        # Register event handler for transcript updates
+        @transcript.event_handler("on_transcript_update")
+        async def on_transcript_update(processor, frame):
+            await transcript_handler.on_transcript_update(processor, frame)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())