from mistral_common.protocol.instruct.messages import AudioURL, AudioURLChunk, TextChunk, UserMessage
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer

repo_id = "mistralai/Voxtral-Mini-3B-2507"
tokenizer = MistralTokenizer.from_hf_hub(repo_id)

text_chunk = TextChunk(
    text="Wat do you think about this audio?"
)
user_msg = UserMessage(
    content=[
        AudioURLChunk(audio_url=AudioURL(url="https://freewavesamples.com/files/Ouch-6.wav")),
        text_chunk,
    ]
)

request = ChatCompletionRequest(messages=[user_msg])
tokenized = tokenizer.encode_chat_completion(request)

# pass tokenized.tokens to your favorite audio model
print(tokenized.tokens)
print(tokenized.audios)

# print text to visually see tokens
print(tokenized.text)