Mistral: Voxtral Small 24B 2507 STT

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, translat…

mistralai/voxtral-small-24b-2507-stt-20260813

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. Input audio is priced at $100 per million seconds.

Specifications & capabilities

Input
audio
Output
transcription
Context window · tokens
0
Published model ID
Voxtral-Small-24B-2507
Capabilities
audioInput, multimodal
Description source ↗

Evaluations

1–20 / 104

Open ASR Leaderboard

2.47%

source id
openASR
leaderboard name
🇵🇹 Portuguese · FLEURS (WER)
dimension
speech
metric
🇵🇹 Portuguese · FLEURS (WER)
rank
2
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/portuguese
suite
OpenASR official public table
datasets
  • FLEURS
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇵🇹 Portuguese · FLEURS (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/portuguese.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
45
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

1.98%

source id
openASR
leaderboard name
🇩🇪 German · FLEURS (WER)
dimension
speech
metric
🇩🇪 German · FLEURS (WER)
rank
2
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/german
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇩🇪 German · FLEURS (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/german.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
46
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

1.87%

source id
openASR
leaderboard name
🇪🇸 Spanish · FLEURS (WER)
dimension
speech
metric
🇪🇸 Spanish · FLEURS (WER)
rank
3
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/spanish
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇪🇸 Spanish · FLEURS (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/spanish.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
45
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

4.04%

source id
openASR
leaderboard name
🇳🇱 Dutch · Average WER
dimension
speech
metric
🇳🇱 Dutch · Average WER
rank
4
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/dutch
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇳🇱 Dutch · Average WER
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/dutch.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
41
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

3.57%

source id
openASR
leaderboard name
fr_fleurs (WER)
dimension
speech
metric
fr_fleurs (WER)
rank
4
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_latest.csv
metric_method
published WER/RTFx
metric_kind
fr_fleurs (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
34
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

3.24%

source id
openASR
leaderboard name
🇳🇱 Dutch · FLEURS (WER)
dimension
speech
metric
🇳🇱 Dutch · FLEURS (WER)
rank
4
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/dutch
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇳🇱 Dutch · FLEURS (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/dutch.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
41
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

2.59%

source id
openASR
leaderboard name
de_fleurs (WER)
dimension
speech
metric
de_fleurs (WER)
rank
4
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_latest.csv
metric_method
published WER/RTFx
metric_kind
de_fleurs (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
34
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

3.77%

source id
openASR
leaderboard name
🇵🇹 Portuguese · Average WER
dimension
speech
metric
🇵🇹 Portuguese · Average WER
rank
5
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/portuguese
suite
OpenASR official public table
datasets
  • FLEURS
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇵🇹 Portuguese · Average WER
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/portuguese.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
45
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

2.58%

source id
openASR
leaderboard name
🇩🇪 German · Average WER
dimension
speech
metric
🇩🇪 German · Average WER
rank
5
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/german
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇩🇪 German · Average WER
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/german.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
46
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

2%

source id
openASR
leaderboard name
Voxpopuli-AA-Cleaned WER (WER)
dimension
speech
metric
Voxpopuli-AA-Cleaned WER (WER)
rank
5
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
metric_method
published WER/RTFx
metric_kind
Voxpopuli-AA-Cleaned WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/open-asr-leaderboard-results/english_short_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
65
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

1.29%

source id
openASR
leaderboard name
🇮🇹 Italian · FLEURS (WER)
dimension
speech
metric
🇮🇹 Italian · FLEURS (WER)
rank
5
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/italian
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇮🇹 Italian · FLEURS (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/italian.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
44
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

3.91%

source id
openASR
leaderboard name
🇫🇷 French · Average WER
dimension
speech
metric
🇫🇷 French · Average WER
rank
6
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/french
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇫🇷 French · Average WER
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/french.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
45
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

3.22%

source id
openASR
leaderboard name
fr_mls (WER)
dimension
speech
metric
fr_mls (WER)
rank
6
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_latest.csv
metric_method
published WER/RTFx
metric_kind
fr_mls (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
34
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

2.99%

source id
openASR
leaderboard name
🇫🇷 French · FLEURS (WER)
dimension
speech
metric
🇫🇷 French · FLEURS (WER)
rank
6
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/french
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇫🇷 French · FLEURS (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/french.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
45
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

5.6%

source id
openASR
leaderboard name
fr_covost (WER)
dimension
speech
metric
fr_covost (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_latest.csv
metric_method
published WER/RTFx
metric_kind
fr_covost (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
34
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

5.5%

source id
openASR
leaderboard name
MCV WER (WER)
dimension
speech
metric
MCV WER (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_fr.csv
metric_method
published WER/RTFx
metric_kind
MCV WER (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_fr.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
40
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

5.06%

source id
openASR
leaderboard name
pt_mls (WER)
dimension
speech
metric
pt_mls (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_latest.csv
metric_method
published WER/RTFx
metric_kind
pt_mls (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
34
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

3.697%

source id
openASR
leaderboard name
Avg (WER)
dimension
speech
metric
Avg (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
suite
hf-audio/multilingual_evals/multilingual_latest.csv
metric_method
published WER/RTFx
metric_kind
Avg (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
hf-audio/multilingual_evals/multilingual_latest.csv
published_at
2026-10-21T14:20:31Z
source_revision
943867e1b478153a2161b0522c130917d0d96b01a780660e00252b573bc2cf13
metric_population
34
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507
Original result ↗

Open ASR Leaderboard

3.25%

source id
openASR
leaderboard name
🇳🇱 Dutch · MCV (WER)
dimension
speech
metric
🇳🇱 Dutch · MCV (WER)
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/dutch
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇳🇱 Dutch · MCV (WER)
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/dutch.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
41
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Open ASR Leaderboard

2.6%

source id
openASR
leaderboard name
🇪🇸 Spanish · Average WER
dimension
speech
metric
🇪🇸 Spanish · Average WER
rank
7
aggregation scope
status
published
direction
lowerIsBetter
conditions
view
multilingual/spanish
suite
OpenASR official public table
datasets
  • FLEURS
  • MCV
  • MLS
metric_method
publisher WER/RTFx for selected public view
space_revision
3b5317f4e49b6cb40502b95065b29fbfe08284ce
publisher_version
13-11-2026
metric_kind
🇪🇸 Spanish · Average WER
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
source_file
public/multilingual/spanish.json
published_at
2026-11-13T11:42:34Z
source_revision
8f2cc9c9f3b01b8670c8640efc67f24a3ea076c2bf5e90e7c674a1a829d69bd7
metric_population
45
benchmark_evaluation
true
source model id
mistralai/Voxtral-Small-24B-2507 🤗
Original result ↗

Published prices

1–4 / 4

Provider specifications & access

1–1 / 1

Voxtral Small 24B 2507 ↗

source model id
mistral.voxtral-small-24b-2507
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • speech
  • text
output_modalities
  • text
capabilities

    Safety assessments

    1–1 / 1

    Foundation Model Transparency Index 2025 ↗

    18 / 100

    source id
    stanfordFMTI
    canonical model id
    mistralai/voxtral-small-24b-2507-stt-20260813
    taxonomy
    transparency
    hazard category
    transparency
    hazard name
    Organization transparency
    policy area
    Mistral
    assessment type
    organization-level disclosure
    metric
    disclosure_score
    result label
    18 / 100
    sample size
    100
    updated at
    2026-11-09T18:08:05.227Z

    Source specification observations

    1–2 / 2

    openRouter ↗

    field
    context_length
    value
    32768
    normalized value
    32768
    scope
    source-model
    source id
    openRouter
    confidence
    1

    openRouter ↗

    field
    max_output_tokens
    value
    26214
    normalized value
    26214
    scope
    source-model
    source id
    openRouter
    confidence
    1

    Original sources

    1–9 / 9

    Hugging Face · mistralai/Voxtral-Small-24B-2507 ↗

    OpenRouter · Model page ↗

    OpenRouter · Model page ↗

    Amazon Web Services · Model page ↗

    Amazon Bedrock · Model documentation ↗

    Amazon Web Services · Catalog ↗

    GitHub · Catalog ↗

    Hugging Face · Catalog ↗

    OpenRouter · Catalog ↗

    Source links

    1–6 / 6

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace