Merge pull request #2821 from shreyas-sarvam/sarvam/stt

Sarvam STT/STTT WS implementation

Author: markbackman

CHANGELOG.md

@@ -9,6 +9,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- Added supprt for Sarvam Speech-to-Text service (`SarvamSTTService`) with streaming WebSocket
+  support for `saarika` (STT) and `saaras` (STT-translate) models.
+
 - Added a new `DeepgramHttpTTSService`, which delivers a meaningful reduction
   in latency when compared to the `DeepgramTTSService`.
 

examples/foundational/07z-interruptible-sarvam-http.py

@@ -22,8 +22,8 @@
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.stt import SarvamSTTService
 from pipecat.services.sarvam.tts import SarvamHttpTTSService
 from pipecat.transcriptions.language import Language
 from pipecat.transports.base_transport import BaseTransport, TransportParams
@@ -63,7 +63,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
 
     # Create an HTTP session
     async with aiohttp.ClientSession() as session:
-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        stt = SarvamSTTService(
+            api_key=os.getenv("SARVAM_API_KEY"),
+            model="saarika:v2.5",
+        )
 
         tts = SarvamHttpTTSService(
             api_key=os.getenv("SARVAM_API_KEY"),

examples/foundational/07z-interruptible-sarvam.py

@@ -24,8 +24,8 @@
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.deepgram.stt import DeepgramSTTService
 from pipecat.services.openai.llm import OpenAILLMService
+from pipecat.services.sarvam.stt import SarvamSTTService
 from pipecat.services.sarvam.tts import SarvamTTSService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -62,7 +62,10 @@
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+    stt = SarvamSTTService(
+        api_key=os.getenv("SARVAM_API_KEY"),
+        model="saarika:v2.5",
+    )
 
     tts = SarvamTTSService(
         api_key=os.getenv("SARVAM_API_KEY"),

pyproject.toml

@@ -93,7 +93,7 @@ rime = [ "pipecat-ai[websockets-base]" ]
 riva = [ "nvidia-riva-client~=2.21.1" ]
 runner = [ "python-dotenv>=1.0.0,<2.0.0", "uvicorn>=0.32.0,<1.0.0", "fastapi>=0.115.6,<0.117.0", "pipecat-ai-small-webrtc-prebuilt>=1.0.0"]
 sambanova = []
-sarvam = [ "pipecat-ai[websockets-base]" ]
+sarvam = [ "sarvamai==0.1.21", "pipecat-ai[websockets-base]" ]
 sentry = [ "sentry-sdk>=2.28.0,<3" ]
 local-smart-turn = [ "coremltools>=8.0", "transformers", "torch>=2.5.0,<3", "torchaudio>=2.5.0,<3" ]
 local-smart-turn-v3 = [ "transformers", "onnxruntime>=1.20.1,<2" ]