Transcription
Models that turn spoken audio into text.
The transcription models behind audio transcription. Each is priced per minute of audio and documents the languages it covers and whether it separates speakers and marks timestamps. Name one directly when a job needs a particular language, diarization, or a lower cost.
17 models
Deepgram Nova-3TranscriptionDeepgram
$0.0043/ min of audio
February 2025
Released
RealtimeLow latency
Gemini 3.5 TranscribeTranscriptionGoogle
~$0.005/ min
August 2026
Released
MultilingualLow cost
GPT TranscribeTranscriptionOpenAI
$0.0045/ min
GPT-4o Transcribe DiarizeTranscriptionOpenAI
$10.00/ 1M tokens
Grok Voice TranscribeTranscriptionX.ai
$0.10/ hour
2026
Released
Low cost
Qwen3 ASR 0.6BTranscriptionQwen· via
DeepInfra
DeepInfra$0.00020/ min
2026
Released
Open sourceFastLow cost
Qwen3 ASR 1.7BTranscriptionQwen· viaDeepInfra
DeepInfra$0.00045/ min
2026
Released
Open sourceMultilingual
Scribe v2TranscriptionElevenLabs
$0.22/ hour
2026
Released
Multilingual
Scribe v2 MedicalTranscriptionElevenLabs
$0.22/ hour
2026
Released
Voxtral Mini 3BTranscriptionMistral· viaDeepInfra
DeepInfra$0.0010/ min
July 2025
Released
Open source
Voxtral Mini Transcribe 2TranscriptionMistral
$0.003/ min
February 2026
Released
Low cost
Voxtral Mini Transcribe 3TranscriptionMistral
$0.0035/ min
October 2026
Released
Low costMultilingual
Voxtral Small 24BTranscriptionMistral· viaDeepInfra
DeepInfra$0.0030/ min
July 2025
Released
Open sourceMultilingual
Voxtral Small Transcribe 3TranscriptionMistral
$0.004/ min
October 2026
Released
Multilingual
Whisper Large v3TranscriptionOpenAI· viaDeepInfra
DeepInfra$0.00045/ min
November 2023
Released
Open sourceLow cost
Whisper Large v3 TurboTranscriptionOpenAI· viaDeepInfra
DeepInfra$0.00020/ min
October 2024
Released
Open sourceFastLow cost
Whisper-1TranscriptionOpenAI
$0.006/ minute
September 2022
Released
Open sourceLow cost