this huggingface.co api & Abc7347 this github AI Model

Introduction of this

Model Details of this

Voxtral Small 1.0 (24B) - 2507

Voxtral Small is an enhancement of Mistral Small 3 , incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.

Learn more about Voxtral in our blog post here and our research paper .

Key Features

Voxtral builds upon Mistral Small 3 with powerful audio understanding capabilities.

Dedicated transcription mode : Voxtral can operate in a pure speech transcription mode to maximize performance. By default, Voxtral automatically predicts the source audio language and transcribes the text accordingly
Long-form context : With a 32k token context length, Voxtral handles audios up to 30 minutes for transcription, or 40 minutes for understanding
Built-in Q&A and summarization : Supports asking questions directly through audio. Analyze audio and generate structured summaries without the need for separate ASR and language models
Natively multilingual : Automatic language detection and state-of-the-art performance in the world’s most widely used languages (English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian)
Function-calling straight from voice : Enables direct triggering of backend functions, workflows, or API calls based on spoken user intents
Highly capable at text : Retains the text understanding capabilities of its language model backbone, Mistral Small 3.1

Benchmark Results

Audio

Average word error rate (WER) over the FLEURS, Mozilla Common Voice and Multilingual LibriSpeech benchmarks:

Text

Usage

The model can be used with the following frameworks;

vllm (recommended) : See here
Transformers 🤗 : See here

Notes :

temperature=0.2 and top_p=0.95 for chat completion ( e.g. Audio Understanding ) and temperature=0.0 for transcription
Multiple audios per message and multiple user turns with audio are supported
Function calling is supported
System prompts are not yet supported

vLLM (recommended)

We recommend using this model with vLLM .

Installation

Make sure to install vllm >= 0.10.0 , we recommend using uv

uv pip install -U "vllm[audio]" --system

Doing so should automatically install mistral_common >= 1.8.1 .

To check:

python -c "import mistral_common; print(mistral_common.__version__)"

Offline

You can test that your vLLM setup works as expected by cloning the vLLM repo:

git clone https://github.com/vllm-project/vllm && cd vllm

and then running:

python examples/offline_inference/audio_language.py --num-audios 2 --model-type voxtral

Serve

We recommend that you use Voxtral-Small-24B-2507 in a server/client setting.

Spin up a server:

vllm serve mistralai/Voxtral-Small-24B-2507 --tokenizer_mode mistral --config_format mistral --load_format mistral --tensor-parallel-size 2 --tool-call-parser mistral --enable-auto-tool-choice

Note: Running Voxtral-Small-24B-2507 on GPU requires ~55 GB of GPU RAM in bf16 or fp16.

To ping the client you can use a simple Python snippet. See the following examples.

Audio Instruct

Leverage the audio capabilities of Voxtral-Small-24B-2507 to chat.

Make sure that your client has mistral-common with audio installed:

pip install --upgrade mistral_common\[audio\]

Python snippet

from mistral_common.protocol.instruct.messages import TextChunk, AudioChunk, UserMessage, AssistantMessage, RawAudio
from mistral_common.audio import Audio
from huggingface_hub import hf_hub_download

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo_type="dataset")
bcn_file = hf_hub_download("patrickvonplaten/audio_samples", "bcn_weather.mp3", repo_type="dataset")

def file_to_chunk(file: str) -> AudioChunk:
    audio = Audio.from_file(file, strict=False)
    return AudioChunk.from_audio(audio)

text_chunk = TextChunk(text="Which speaker is more inspiring? Why? How are they different from each other? Answer in French.")
user_msg = UserMessage(content=[file_to_chunk(obama_file), file_to_chunk(bcn_file), text_chunk]).to_openai()

print(30 * "=" + "USER 1" + 30 * "=")
print(text_chunk.text)
print("\n\n")

response = client.chat.completions.create(
    model=model,
    messages=[user_msg],
    temperature=0.2,
    top_p=0.95,
)
content = response.choices[0].message.content

print(30 * "=" + "BOT 1" + 30 * "=")
print(content)
print("\n\n")
# The model could give the following answer:
# ```L'orateur le plus inspirant est le président.
# Il est plus inspirant parce qu'il parle de ses expériences personnelles
# et de son optimisme pour l'avenir du pays.
# Il est différent de l'autre orateur car il ne parle pas de la météo,
# mais plutôt de ses interactions avec les gens et de son rôle en tant que président.```

messages = [
    user_msg,
    AssistantMessage(content=content).to_openai(),
    UserMessage(content="Ok, now please summarize the content of the first audio.").to_openai()
]
print(30 * "=" + "USER 2" + 30 * "=")
print(messages[-1]["content"])
print("\n\n")

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=0.2,
    top_p=0.95,
)
content = response.choices[0].message.content
print(30 * "=" + "BOT 2" + 30 * "=")
print(content)

Transcription

Voxtral-Small-24B-2507 has powerful transcription capabilities!

Make sure that your client has mistral-common with audio installed:

pip install --upgrade mistral_common\[audio\]

Python snippet

from mistral_common.protocol.transcription.request import TranscriptionRequest
from mistral_common.protocol.instruct.messages import RawAudio
from mistral_common.audio import Audio
from huggingface_hub import hf_hub_download

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

obama_file = hf_hub_download("patrickvonplaten/audio_samples", "obama.mp3", repo_type="dataset")
audio = Audio.from_file(obama_file, strict=False)

audio = RawAudio.from_audio(audio)
req = TranscriptionRequest(model=model, audio=audio, language="en", temperature=0.0).to_openai(exclude=("top_p", "seed"))

response = client.audio.transcriptions.create(**req)
print(response)

Function Calling

Voxtral has some experimental function calling support. You can try as shown below.

Make sure that your client has mistral-common with audio installed:

pip install --upgrade mistral_common\[audio\]

Python snippet

from mistral_common.protocol.instruct.messages import AudioChunk, UserMessage, TextChunk
from mistral_common.protocol.transcription.request import TranscriptionRequest
from mistral_common.protocol.instruct.tool_calls import Function, Tool

from mistral_common.audio import Audio
from huggingface_hub import hf_hub_download

from openai import OpenAI

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://<your-server-host>:8000/v1"

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id

tool = Tool(
    function=Function(
        name="get_current_weather",
        description="Get the current weather",
        parameters={
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "format": {
                    "type": "string",
                    "enum": ["celsius", "fahrenheit"],
                    "description": "The temperature unit to use. Infer this from the user's location.",
                },
            },
            "required": ["location", "format"],
        },
    )
)
tools = [tool.to_openai()]


weather_like = hf_hub_download("patrickvonplaten/audio_samples", "fn_calling.wav", repo_type="dataset")

def file_to_chunk(file: str) -> AudioChunk:
    audio = Audio.from_file(file, strict=False)
    return AudioChunk.from_audio(audio)

audio_chunk = file_to_chunk(weather_like)

print(30 * "=" + "Transcription" + 30 * "=")
req = TranscriptionRequest(model=model, audio=audio_chunk.input_audio, language="en", temperature=0.0).to_openai(exclude=("top_p", "seed"))
response = client.audio.transcriptions.create(**req)
print(response.text) # How is the weather in Madrid at the moment?
print("\n")


print(30 * "=" + "Function calling" + 30 * "=")
audio_chunk = file_to_chunk(weather_like)
user_msg = UserMessage(content=[audio_chunk]).to_openai()
response = client.chat.completions.create(
    model=model,
    messages=[user_msg],
    temperature=0.2,
    top_p=0.95,
    tools=[tool.to_openai()]
)
print(30 * "=" + "BOT 1" + 30 * "=")
print(response.choices[0].message.tool_calls)
print("\n\n")

Transformers 🤗

Starting with transformers >= 4.54.0 and above, you can run Voxtral natively!

Install Transformers:

pip install -U transformers

Make sure to have mistral-common >= 1.8.1 installed with audio dependencies:

pip install --upgrade "mistral-common[audio]"

Audio Instruct

➡️ multi-audio + text instruction

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Small-24B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/mary_had_lamb.mp3",
            },
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
            },
            {"type": "text", "text": "What sport and what nursery rhyme are referenced?"},
        ],
    }
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

➡️ multi-turn

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Small-24B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
            },
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
            },
            {"type": "text", "text": "Describe briefly what you can hear."},
        ],
    },
    {
        "role": "assistant",
        "content": "The audio begins with the speaker delivering a farewell address in Chicago, reflecting on his eight years as president and expressing gratitude to the American people. The audio then transitions to a weather report, stating that it was 35 degrees in Barcelona the previous day, but the temperature would drop to minus 20 degrees the following day.",
    },
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
            },
            {"type": "text", "text": "Ok, now compare this new audio with the previous one."},
        ],
    },
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

➡️ text only

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Small-24B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Why should AI models be open-sourced?",
            },
        ],
    }
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

➡️ audio only

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Small-24B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversation = [
    {
        "role": "user",
        "content": [
            {
                "type": "audio",
                "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
            },
        ],
    }
]

inputs = processor.apply_chat_template(conversation)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated response:")
print("=" * 80)
print(decoded_outputs[0])
print("=" * 80)

➡️ batched inference

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Small-24B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

conversations = [
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3",
                },
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
                },
                {
                    "type": "text",
                    "text": "Who's speaking in the speach and what city's weather is being discussed?",
                },
            ],
        }
    ],
    [
        {
            "role": "user",
            "content": [
                {
                    "type": "audio",
                    "path": "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/winning_call.mp3",
                },
                {"type": "text", "text": "What can you tell me about this audio?"},
            ],
        }
    ],
]

inputs = processor.apply_chat_template(conversations)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated responses:")
print("=" * 80)
for decoded_output in decoded_outputs:
    print(decoded_output)
    print("=" * 80)

Transcription

➡️ transcribe

from transformers import VoxtralForConditionalGeneration, AutoProcessor
import torch

device = "cuda"
repo_id = "mistralai/Voxtral-Small-24B-2507"

processor = AutoProcessor.from_pretrained(repo_id)
model = VoxtralForConditionalGeneration.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map=device)

inputs = processor.apply_transcription_request(language="en", audio="https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/obama.mp3", model_id=repo_id)
inputs = inputs.to(device, dtype=torch.bfloat16)

outputs = model.generate(**inputs, max_new_tokens=500)
decoded_outputs = processor.batch_decode(outputs[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)

print("\nGenerated responses:")
print("=" * 80)
for decoded_output in decoded_outputs:
    print(decoded_output)
    print("=" * 80)

Runs of Abc7347 this on huggingface.co

Total runs

-1

24-hour runs

-2

3-day runs

7-day runs

30-day runs

More Information About this huggingface.co Model

More this license Visit here:

https://choosealicense.com/licenses/apache-2.0

this huggingface.co

this huggingface.co is an AI model on huggingface.co that provides this's model effect (), which can be used instantly with this Abc7347 this model. huggingface.co supports a free trial of the this model, and also provides paid use of the this. Support call this model through api, including Node.js, Python, http.

this huggingface.co Url

https://huggingface.co/Abc7347/this

Abc7347 this online free

this huggingface.co is an online trial and call api platform, which integrates this's modeling effects, including api services, and provides a free online trial of this, you can try this online for free by clicking the link below.

Abc7347 this online free url in huggingface.co:

https://huggingface.co/Abc7347/this

this install

this is an open source model from GitHub that offers a free installation service, and any user can find this on GitHub to install. At the same time, huggingface.co provides the effect of this install, users can directly use this installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

this install url in huggingface.co:

https://huggingface.co/Abc7347/this

huggingface.co

Abc7347/Llama-3.2-3B-Instruct-uncensored-Q4_K_M-GGUF

Total runs: 901

Run Growth: 459

Growth Rate: 50.94%

Updated:October 02 2024

huggingface.co

Abc7347/12bgguf

Total runs: 574

Run Growth: 233

Growth Rate: 40.59%

Updated:February 05 2026

huggingface.co

Abc7347/4bgguf

Total runs: 511

Run Growth: -98

Growth Rate: -19.18%

Updated:February 05 2026

huggingface.co

Abc7347/gguf27bv3

Total runs: 337

Run Growth: -217

Growth Rate: -64.39%

Updated:February 05 2026

huggingface.co

Abc7347/Huihui-Qwen3-4B-Instruct-2507-abliterated-Q4_K_M-GGUF

Total runs: 175

Run Growth: -46

Growth Rate: -26.29%

Updated:November 03 2025

huggingface.co

Abc7347/Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF

Total runs: 80

Run Growth: -19

Growth Rate: -23.75%

Updated:May 09 2025

huggingface.co

Abc7347/Dolphin3.0-Llama3.2-3B-Q4_K_M-GGUF

Total runs: 69

Run Growth: 5

Growth Rate: 7.25%

Updated:January 06 2025

huggingface.co

Abc7347/BlackSheep-Llama3.2-3B-Q4_K_M-GGUF

Total runs: 52

Run Growth: 4

Growth Rate: 7.69%

Updated:October 02 2024

huggingface.co

Abc7347/BlackSheep-Llama3.2-3B-Q8_0-GGUF

Total runs: 23

Run Growth: -2

Growth Rate: -8.70%

Updated:October 02 2024

huggingface.co

Abc7347/abccc

Total runs: 17

Run Growth: 0

Growth Rate: 0.00%

Updated:January 28 2026

huggingface.co

Abc7347/Qwen3-4B-Base-Q4_K_M-GGUF

Total runs: 15

Run Growth: -3

Growth Rate: -20.00%

Updated:October 30 2025

huggingface.co

Abc7347/Llama-3.2-MedIT-3B-R1-Q4_K_M-GGUF

Total runs: 12

Run Growth: 2

Growth Rate: 16.67%

Updated:February 21 2025

huggingface.co

Abc7347/120bf16

Total runs: 12

Run Growth: -7

Growth Rate: -58.33%

Updated:March 15 2026

huggingface.co

Abc7347/clone

Total runs: 12

Run Growth: 5

Growth Rate: 41.67%

Updated:January 25 2026

huggingface.co

Abc7347/Llama-3.2-3B-Overthinker-Q8_0-GGUF

Total runs: 11

Run Growth: -9

Growth Rate: -81.82%

Updated:October 18 2024

huggingface.co

Abc7347/aceaudio

Total runs: 11

Run Growth: 2

Growth Rate: 18.18%

Updated:February 07 2026

huggingface.co

Abc7347/gemm2b

Total runs: 10

Run Growth: 5

Growth Rate: 50.00%

Updated:April 06 2026

huggingface.co

Abc7347/clone4bit

Total runs: 10

Run Growth: -3

Growth Rate: -30.00%

Updated:January 25 2026

huggingface.co

Abc7347/Dolphy-1.0-Q4_0-GGUF

Total runs: 10

Run Growth: -14

Growth Rate: -140.00%

Updated:October 27 2025

huggingface.co

Abc7347/80qwen

Total runs: 9

Run Growth: -6

Growth Rate: -66.67%

Updated:March 15 2026

huggingface.co

Abc7347/dolly-v2-3b-Q4_K_M-GGUF

Total runs: 9

Run Growth: -54

Growth Rate: -600.00%

Updated:October 27 2025

huggingface.co

Abc7347/copytext27binstructgmn

Total runs: 7

Run Growth: 0

Growth Rate: 0.00%

Updated:February 05 2026

huggingface.co

Abc7347/3.5copy400BMoE

Total runs: 7

Run Growth: -1

Growth Rate: -14.29%

Updated:February 25 2026

huggingface.co

Abc7347/gemm4-26bmoe-clond

Total runs: 6

Run Growth: 1

Growth Rate: 16.67%

Updated:April 06 2026

huggingface.co

Abc7347/Llama-3.1-8B-Instruct-Q8_0-GGUF

Total runs: 6

Run Growth: -13

Growth Rate: -216.67%

Updated:October 15 2024

huggingface.co

Abc7347/3.5copy35bMoE

Total runs: 6

Run Growth: 2

Growth Rate: 33.33%

Updated:February 25 2026

huggingface.co

Abc7347/gemm4-31b-dense

Total runs: 5

Run Growth: 0

Growth Rate: 0.00%

Updated:April 06 2026

huggingface.co

Abc7347/gemm4b

Total runs: 5

Run Growth: -1

Growth Rate: -20.00%

Updated:April 06 2026

huggingface.co

Abc7347/3.6-27bcodebeastclone

Total runs: 4

Run Growth: 1

Growth Rate: 25.00%

Updated:April 23 2026

huggingface.co

Abc7347/3.6a3b-35b

Total runs: 3

Run Growth: -1

Growth Rate: -33.33%

Updated:April 16 2026

Abc7347 / this

Introduction of this

Model Details of this

Voxtral Small 1.0 (24B) - 2507

Key Features

Benchmark Results

Audio

Text

Usage

vLLM (recommended)

Installation

Offline

Serve

Audio Instruct

Transcription

Function Calling

Transformers 🤗

Audio Instruct

Transcription

Runs of Abc7347 this on huggingface.co

More Information About this huggingface.co Model

More this license Visit here:

this huggingface.co

this huggingface.co Url

Abc7347 this online free

Abc7347 this online free url in huggingface.co:

this install

this install url in huggingface.co:

Url of this

this huggingface.co Url

Provider of this huggingface.co

Other API from Abc7347