Explore models.

2,849 models1,625 with prices34 metricsUpdated Oct 22, 2026 ↗

Measured modelsVoxpopuli-AA-Cleaned WER

Clear benchmark ×

Choose a category in More filters to see relevant price sorts.

65 models · Transcription · Voxpopuli-AA-Cleaned WER · newest firstPage 2 / 3

More filters

gladiaDiscovered 5 days ago

gladia/solaria-3

5 languages

Audio inputTranscription

Voxpopuli-AA-Cleaned WERgladia/solaria-32.76% WER

Price not listed

+Compare

googleDiscovered 5 days ago

google/gemma-4-12B-it

140 languages · Decoder: Transformer

Audio inputTranscription

Voxpopuli-AA-Cleaned WERgoogle/gemma-4-12B-it4.18% WER

Price not listed

+Compare

googleDiscovered 5 days ago

google/gemma-4-E2B-it

140 languages · Encoder: Conformer · Decoder: Transformer

Audio inputTranscription

Voxpopuli-AA-Cleaned WERgoogle/gemma-4-E2B-it5.66% WER

Price not listed

+Compare

googleDiscovered 5 days ago

google/gemma-4-E4B-it

7.94B parameters · 140 languages · Encoder: Conformer · Decoder: Transformer

7.94BAudio inputTranscription

Voxpopuli-AA-Cleaned WERgoogle/gemma-4-E4B-it4.09% WER

Price not listed

+Compare

HojoAIDiscovered 5 days ago

HojoAI/Hojo-ASR-V1

5.18B parameters · 2 languages · Encoder: Qwen3-Omni encoder · Decoder: Qwen3-4B

5.18BAudio inputTranscription

Voxpopuli-AA-Cleaned WERHojoAI/Hojo-ASR-V13.11% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-4.0-1b-speech

2B parameters · 6 languages · Encoder: Conformer-based · Decoder: Granite

2BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-4.0-1b-speech4.41% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-speech-3.3-2b

3B parameters · 5 languages · Encoder: Conformer-based · Decoder: Granite

3BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-speech-3.3-2b4.52% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-speech-3.3-8b

9B parameters · 5 languages · Encoder: Conformer-based · Decoder: Granite

9BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-speech-3.3-8b4.54% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-speech-4.1-2b

2B parameters · 6 languages · Encoder: Conformer-based · Decoder: Granite

2BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-speech-4.1-2b4.18% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-speech-4.1-2b-nar

2B parameters · 5 languages · Encoder: Conformer-based · Decoder: Hybrid CTC-LLM

2BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-speech-4.1-2b-nar4.25% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-speech-5.0-470m-turboctc

0.47B parameters · Encoder: Streaming-style Conformer · Decoder: CTC

0.47BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-speech-5.0-470m-turboctc4.9% WER

Price not listed

+Compare

ibm-graniteDiscovered 5 days ago

ibm-granite/granite-speech-5.0-470m-turboctc-nc

0.47B parameters · Encoder: Streaming-style Conformer · Decoder: CTC

0.47BAudio inputTranscription

Voxpopuli-AA-Cleaned WERibm-granite/granite-speech-5.0-470m-turboctc-nc4.67% WER

Price not listed

+Compare

metaDiscovered 5 days ago

meta/muse-voice-transcribe

25 languages

Audio inputTranscription

Voxpopuli-AA-Cleaned WERmeta/muse-voice-transcribe2.02% WER

Price not listed

+Compare

microsoftDiscovered 5 days ago

microsoft/azure-speech-06-2026

25 languages · Decoder: LLM

Audio inputTranscription

Voxpopuli-AA-Cleaned WERmicrosoft/azure-speech-06-20263.87% WER

Price not listed

+Compare

microsoftDiscovered 5 days ago

microsoft/azure-speech-07-2026

25 languages · Decoder: LLM

Audio inputTranscription

Voxpopuli-AA-Cleaned WERmicrosoft/azure-speech-07-20261.65% WER

Price not listed

+Compare

microsoftDiscovered 5 days ago

microsoft/Phi-4-multimodal-instruct

6B parameters · 8 languages · Encoder: Conformer-based · Decoder: Phi-4-Mini-Instruct

6BAudio inputTranscription

Voxpopuli-AA-Cleaned WERmicrosoft/Phi-4-multimodal-instruct4.18% WER

Price not listed

+Compare

microsoftDiscovered 5 days ago

microsoft/VibeVoice-ASR-HF

8B parameters · 50 languages · Encoder: Custom · Decoder: Qwen2

8BAudio inputTranscription

Voxpopuli-AA-Cleaned WERmicrosoft/VibeVoice-ASR-HF2.02% WER

Price not listed

+Compare

mistralaiDiscovered 5 days ago

mistralai/Voxtral-Mini-4B-Realtime-2602

4B parameters · 13 languages · Encoder: Custom · Decoder: Transformer

4BAudio inputTranscription

Voxpopuli-AA-Cleaned WERmistralai/Voxtral-Mini-4B-Realtime-26022.6% WER

Price not listed

+Compare

modulateDiscovered 5 days ago

modulate/multilingual

99 languages

Audio inputTranscription

Voxpopuli-AA-Cleaned WERmodulate/multilingual3.55% WER

Price not listed

+Compare

nvidiaDiscovered 5 days ago

nvidia/canary-1b-v2

1B parameters · 25 languages · Encoder: Conformer-based · Decoder: Transformer

1BAudio inputTranscription

Voxpopuli-AA-Cleaned WERnvidia/canary-1b-v24.39% WER

Price not listed

+Compare

nvidiaDiscovered 5 days ago

nvidia/canary-qwen-2.5b

2.5B parameters · Encoder: Conformer-based · Decoder: Qwen2

2.5BAudio inputTranscription

Voxpopuli-AA-Cleaned WERnvidia/canary-qwen-2.5b4.14% WER

Price not listed

+Compare

nvidiaDiscovered 5 days ago

nvidia/nemotron-3.5-asr-streaming-0.6b

0.64B parameters · 40 languages · Encoder: FastConformer (cache-aware) · Decoder: RNNT

0.64BAudio inputTranscription

Voxpopuli-AA-Cleaned WERnvidia/nemotron-3.5-asr-streaming-0.6b4.24% WER

Price not listed

+Compare

nvidiaDiscovered 5 days ago

nvidia/nemotron-speech-streaming-en-0.6b

0.62B parameters · Encoder: FastConformer (cache-aware) · Decoder: RNNT

0.62BAudio inputTranscription

Voxpopuli-AA-Cleaned WERnvidia/nemotron-speech-streaming-en-0.6b2.4% WER

Price not listed

+Compare

nvidiaDiscovered 5 days ago

nvidia/parakeet-ctc-1.1b

1.1B parameters · Encoder: Conformer-based · Decoder: CTC

1.1BAudio inputTranscription

Voxpopuli-AA-Cleaned WERnvidia/parakeet-ctc-1.1b3.24% WER

Price not listed

+Compare