diff --git a/src/pipecat/services/nvidia/tts.py b/src/pipecat/services/nvidia/tts.py index 672461dff..91eb138e0 100644 --- a/src/pipecat/services/nvidia/tts.py +++ b/src/pipecat/services/nvidia/tts.py @@ -169,7 +169,7 @@ class NvidiaTTSService(TTSService): await asyncio.to_thread(read_audio_responses, queue) # Wait for the thread to start. - resp = await asyncio.wait_for(queue.get(), timeout=RIVA_TTS_TIMEOUT_SECS) + resp = await asyncio.wait_for(queue.get(), timeout=NVIDIA_TTS_TIMEOUT_SECS) while resp: await self.stop_ttfb_metrics() frame = TTSAudioRawFrame( @@ -178,7 +178,7 @@ class NvidiaTTSService(TTSService): num_channels=1, ) yield frame - resp = await asyncio.wait_for(queue.get(), timeout=RIVA_TTS_TIMEOUT_SECS) + resp = await asyncio.wait_for(queue.get(), timeout=NVIDIA_TTS_TIMEOUT_SECS) except asyncio.TimeoutError: logger.error(f"{self} timeout waiting for audio response") yield ErrorFrame(error=f"{self} error: {e}") diff --git a/src/pipecat/services/riva/stt.py b/src/pipecat/services/riva/stt.py index a64d237f0..9dcb44948 100644 --- a/src/pipecat/services/riva/stt.py +++ b/src/pipecat/services/riva/stt.py @@ -31,5 +31,5 @@ with warnings.catch_warnings(): RivaSTTService = NvidiaSTTService language_to_riva_language = language_to_nvidia_riva_language -RivaSegmentedSTTService = NvidiaSegmentedTTSService -ParakeetSTTService = NvidiaTTSService +RivaSegmentedSTTService = NvidiaSegmentedSTTService +ParakeetSTTService = NvidiaSTTService diff --git a/uv.lock b/uv.lock index 9a1ca9135..17bdef385 100644 --- a/uv.lock +++ b/uv.lock @@ -1,5 +1,5 @@ version = 1 -revision = 3 +revision = 2 requires-python = ">=3.10" resolution-markers = [ "python_full_version >= '3.13'", @@ -4564,6 +4564,9 @@ neuphonic = [ noisereduce = [ { name = "noisereduce" }, ] +nvidia = [ + { name = "nvidia-riva-client" }, +] openai = [ { name = "websockets" }, ] @@ -4706,6 +4709,7 @@ requires-dist = [ { name = "noisereduce", marker = "extra == 'noisereduce'", specifier = "~=3.0.3" }, { name = "numba", specifier = "==0.61.2" }, { name = "numpy", specifier = ">=1.26.4,<3" }, + { name = "nvidia-riva-client", marker = "extra == 'nvidia'", specifier = "~=2.21.1" }, { name = "nvidia-riva-client", marker = "extra == 'riva'", specifier = "~=2.21.1" }, { name = "onnxruntime", marker = "extra == 'local-smart-turn-v3'", specifier = ">=1.20.1,<2" }, { name = "onnxruntime", marker = "extra == 'silero'", specifier = ">=1.20.1,<2" }, @@ -4767,7 +4771,7 @@ requires-dist = [ { name = "wait-for2", marker = "python_full_version < '3.12'", specifier = ">=0.4.1" }, { name = "websockets", marker = "extra == 'websockets-base'", specifier = ">=13.1,<16.0" }, ] -provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "krisp", "langchain", "livekit", "lmnt", "local", "local-smart-turn", "local-smart-turn-v3", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "nim", "noisereduce", "openai", "openpipe", "openrouter", "perplexity", "playht", "qwen", "remote-smart-turn", "rime", "riva", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"] +provides-extras = ["aic", "anthropic", "assemblyai", "asyncai", "aws", "aws-nova-sonic", "azure", "cartesia", "cerebras", "daily", "deepgram", "deepseek", "elevenlabs", "fal", "fireworks", "fish", "gladia", "google", "grok", "groq", "gstreamer", "heygen", "hume", "inworld", "koala", "krisp", "langchain", "livekit", "lmnt", "local", "local-smart-turn", "local-smart-turn-v3", "mcp", "mem0", "mistral", "mlx-whisper", "moondream", "neuphonic", "nim", "noisereduce", "openai", "openpipe", "openrouter", "perplexity", "playht", "qwen", "remote-smart-turn", "rime", "riva", "nvidia", "runner", "sagemaker", "sambanova", "sarvam", "sentry", "silero", "simli", "soniox", "soundfile", "speechmatics", "strands", "tavus", "together", "tracing", "ultravox", "webrtc", "websocket", "websockets-base", "whisper"] [package.metadata.requires-dev] dev = [