Speech-to-text API
OpenAI Speech to Text API
by OpenAI
OpenAI's speech-to-text API for developers, which transcribes recorded audio files and live audio into text.
- API
Key figures
Every figure about OpenAI Speech to Text API
Each figure is a row of a research dataset. Open it for the exact words of its source or the exact request it was read from.
Speech Recognition Accuracy: Word Error Rates
- GPT-4o Mini Transcribe OpenAI20264.5 WER %
- GPT-4o Transcribe OpenAI20264 WER %
- GPT Transcribe, OpenAI OpenAI20263.3 WER %
- GPT-4o mini Transcribe, FLEURS Arabic202514.02 WER %
- GPT-4o mini Transcribe, CHiME-4 English202511.35 WER %
- GPT-4o mini Transcribe, CV Arabic202551.68 WER %
- GPT-4o mini Transcribe, CV German20256.72 WER %
- GPT-4o mini Transcribe, CV English202513.15 WER %
- GPT-4o mini Transcribe, CV Spanish20256.1 WER %
- GPT-4o mini Transcribe, CV French202510.75 WER %
- GPT-4o mini Transcribe, CV Hindi202539.06 WER %
- GPT-4o mini Transcribe, CV Italian20256.16 WER %
- GPT-4o mini Transcribe, CV Dutch20256.47 WER %
- GPT-4o mini Transcribe, CV Portuguese20259.95 WER %
- GPT-4o mini Transcribe, Earnings-21202510.09 WER %
- GPT-4o mini Transcribe, Earnings-22202512.27 WER %
- GPT-4o mini Transcribe, FLEURS German20253.76 WER %
- GPT-4o mini Transcribe, FLEURS English20253.19 WER %
- GPT-4o mini Transcribe, FLEURS Spanish20252.58 WER %
- GPT-4o mini Transcribe, FLEURS French20254.51 WER %
- GPT-4o mini Transcribe, FLEURS Italian20252.02 WER %
- GPT-4o mini Transcribe, FLEURS Dutch20255.54 WER %
- GPT-4o mini Transcribe, FLEURS20253.54 WER %
- GPT-4o mini Transcribe, GigaSpeech202514.8 WER %
Other speech-to-text apis
- Alibaba Cloud Model Studio speech recognitionAlibaba Cloud
- Amazon TranscribeAmazon Web Services
- AmiVoice APIAdvanced Media
- Apple SpeechAnalyzerApple
- AssemblyAIAssemblyAI
- Azure AI SpeechMicrosoft
- Baidu Speech RecognitionBaidu
- Cartesia InkCartesia
- Cloudflare Workers AI speech-to-textCloudflare
- DeepgramDeepgram
- DeepInfra speech-to-textDeepInfra
- ElevenLabs ScribeElevenLabs
- fal speech-to-textfal
- Fireworks AI audio transcriptionFireworks AI
- Gemini API transcriptionGoogle
- GladiaGladia
- Google Cloud Speech-to-TextGoogle Cloud
- Gradium Speech-to-TextGradium
- Grok Speech to TextSpaceXSI (xAI)
- GroqCloud Speech to TextGroq
- IBM Watson Speech to TextIBM
- iFlytek Speech RecognitioniFlytek
- Lemonfox.ai Speech-to-Text APILemonfox.ai
- Meta Muse Voice TranscribeMeta
- Microsoft MAI-TranscribeMicrosoft AI
- Mistral Voxtral TranscribeMistral AI
- Modulate Velma TranscribeModulate
- NAVER CLOVA SpeechNAVER Cloud
- Oracle Cloud Infrastructure SpeechOracle
- Phonexia Speech to TextPhonexia