importsoundfileassfimporttorchfromdatasetsimportAudio,load_datasetfromtransformersimportpipelinedevice="cuda"iftorch.cuda.is_available()else"cpu""""CSM"""pipe=pipeline("text-to-audio",model="sesame/csm-1b",device=device)# -- minimal TTS exampletorch.manual_seed(0)outputs=pipe("Hello from Sesame.")# instead of pipe("[0]Hello from Sesame.")fn="csm_pipeline_tts.wav"sf.write(fn,outputs["audio"],outputs["sampling_rate"])print(f"Audio saved to{fn}")# -- minimal TTS example with voice cloningtorch.manual_seed(0)ds=load_dataset("hf-internal-testing/dailytalk-dummy",split="train")ds=ds.cast_column("audio",Audio(sampling_rate=24000))conversation= [# audio/text pair(s) for voice cloning    {"role":"0","content": [            {"type":"text","text":"What are you working on?"},            {"type":"audio","path":ds[0]["audio"]["array"]},        ],    },# desired audio response for voice cloning    {"role":"0","content": [{"type":"text","text":"How much money can you spend?"}]},]outputs=pipe(conversation)fn="csm_pipeline_voice_cloning.wav"sf.write(fn,outputs["audio"],outputs["sampling_rate"])print(f"Audio saved to{fn}")"""Dia"""pipe=pipeline("text-to-audio",model="nari-labs/Dia-1.6B-0626",device=device)# -- minimal TTS exampletorch.manual_seed(42)outputs=pipe("Dia is an open weights text to dialogue model.",# instead of pipe("[S1] Dia is an open weights text to dialogue model..")generate_kwargs={"max_new_tokens":256},)fn="dia_pipeline_tts.wav"sf.write(fn,outputs["audio"],outputs["sampling_rate"])print(f"Audio saved to{fn}")# -- minimal conversation example# note: Dia doesn't support chat template for voice cloning# explicit model loading should be used instead: https://huggingface.co/nari-labs/Dia-1.6B-0626#generation-with-text-and-audio-voice-cloningtorch.manual_seed(0)outputs=pipe("[S1] Dia is an open weights text to dialogue model. [S2] That's cool, tell me how it works.",)fn="dia_pipeline_conversation.wav"sf.write(fn,outputs["audio"],outputs["sampling_rate"])print(f"Audio saved to{fn}")

importsoundfileassfimporttorchfromdatasetsimportAudio,load_datasetfromtransformersimportpipelinedevice="cuda"iftorch.cuda.is_available()else"cpu"pipe=pipeline("text-to-audio",model="sesame/csm-1b",device=device)# prepare inputds=load_dataset("hf-internal-testing/dailytalk-dummy",split="train")ds=ds.cast_column("audio",Audio(sampling_rate=24000))conversation= [# -- audio/text pair(s) for voice cloning    {"role":"0","content": [            {"type":"text","text":"What are you working on?"},             {"type":"audio","path":ds[0]["audio"]["array"]},        ],    },# -- desired audio response for voice cloning    {"role":"0","content": [{"type":"text","text":"How much money can you spend?"}]},]outputs=pipe(conversation)fn="csm_pipeline_voice_cloning.wav"sf.write(fn,outputs["audio"],outputs["sampling_rate"])print(f"Audio saved to{fn}")