Transcribe AI

Audio Input
Drop an audio file or click to browse
WAV, MP3, FLAC, OGG, M4A
×
Transcript
Transcript
Transcript

Cohere Transcribe

Params2B
ArchConformer Enc-Dec
Langs14
Avg WER5.42%
SourceHuggingFace

Qwen3-ASR

Params1.7B
ArchQwen3-Omni Encoder
Langs52
Avg WER--
SourceHuggingFace

Granite Speech

Params1B
ArchConformer + LLM
Langs6
Avg WER5.52%
SourceHuggingFace

Hardware

GPUNVIDIA Blackwell
Memory128 GB unified
CPUNVIDIA Grace (ARM)
PrecisionBF16
FrameworkPyTorch