Compare Whisper With Faster and Newer Transcription APIs
Whisper is the reference point in our speech-to-text API comparison, versus Incredibly Fast Whisper's speed, GPT-4o Transcribe's vocabulary biasing, and diarization options.
Convert speech in audio to text
{
"audio": "https://replicate.delivery/mgxm/e5159b1b-508a-4be4-b892-e1eb47850bdc/OSR_uk_000_0050_8k.wav",
"model": "large-v3",
"translate": false,
"temperature": 0,
"transcription": "plain text",
"suppress_tokens": "-1",
"logprob_threshold": -1,
"no_speech_threshold": 0.6,
"condition_on_previous_text": true,
"compression_ratio_threshold": 2.4,
"temperature_increment_on_fallback": 0.2
}
Transcribe with large-v3 model. Detected language: English 0%| | 0/5241 [00:00<?, ?frames/s] 35%|███▌ | 1860/5241 [00:03<00:06, 522.23frames/s] 93%|█████████▎| 4860/5241 [00:08<00:00, 583.46frames/s] 100%|██████████| 5241/5241 [00:10<00:00, 479.51frames/s] 100%|██████████| 5241/5241 [00:10<00:00, 506.10frames/s]
8099696689d249cf8b122d833c36ac3f75505c666a395ca40ef26f68e7d3d16e