Speech-to-text models

69 models listed.

Models

Models
Model	Maker	Kind	Released	Context	Input $/1M	Output $/1M
Scribe v2 MedicalScribe	ElevenLabs	Speech-to-text	11 Sep 2026	—	—	—
MAI-Transcribe-2MAI-Transcribe	Microsoft	Speech-to-text	3 Sep 2026	—	—	—
VibeVoice-ASR-Streaming (1.5B / 7B)VibeVoice ASR · Open weights	Microsoft	Speech-to-text	2 Sep 2026	—	—	—
Grok Voice Transcribe 2.0Grok Voice Transcribe	SpaceXAI (xAI)	Speech-to-text	Sep 2026	—	—	—
Gemini 3.5 TranscribeGemini Transcribe	Google DeepMind	Speech-to-text	26 Aug 2026	—	$2.00	$12.00
Gemini 3.5 Transcribe LiveGemini Transcribe	Google DeepMind	Speech-to-text	26 Aug 2026	—	$3.50	$21.00
Granite Speech 5.0 470M TurboCTCGranite Speech · Open weights	IBM	Speech-to-text	4 Aug 2026	—	—	—
Qwen-Audio-3.0-ASRQwen-ASR	Alibaba Group	Speech-to-text	30 Jul 2026	—	—	—
GPT Live TranscribeGPT transcription models	OpenAI	Speech-to-text	28 Jul 2026	—	—	—
GPT TranscribeGPT transcription models	OpenAI	Speech-to-text	28 Jul 2026	—	—	—
Cohere Transcribe ArabicCohere Transcribe · Open weights	Cohere	Speech-to-text	Jul 2026	—	—	—
MAI-Transcribe-1.5MAI-Transcribe · Legacy	Microsoft	Speech-to-text	2 Jun 2026	—	—	—
Nemotron 3.5 ASR Streaming 0.6BNemotron Speech (ASR) · Open weights	NVIDIA	Speech-to-text	15 May 2026	—	—	—
GPT-Realtime-WhisperGPT transcription models	OpenAI	Speech-to-text	7 May 2026	16K	—	—
Granite Speech 4.1 2B (and 2B-plus, 2B-NAR)Granite Speech · Open weights	IBM	Speech-to-text	16 Apr 2026	—	—	—
MAI-Transcribe-1MAI-Transcribe · Legacy	Microsoft	Speech-to-text	2 Apr 2026	—	—	—
Grok Voice Transcribe 1.0Grok Voice Transcribe	SpaceXAI (xAI)	Speech-to-text	Apr 2026	—	—	—
StepAudio 2.5 ASRStep ASR · Legacy	StepFun	Speech-to-text	Apr 2026	—	—	—
Cohere TranscribeCohere Transcribe · Open weights	Cohere	Speech-to-text	24 Mar 2026	—	—	—
Granite 4.0 1B SpeechGranite Speech · Legacy · Open weights	IBM	Speech-to-text	27 Feb 2026	—	—	—
Voxtral Mini Transcribe 2Voxtral Transcribe	Mistral AI	Speech-to-text	4 Feb 2026	—	—	—
Voxtral Mini Transcribe RealtimeVoxtral Transcribe · Open weights	Mistral AI	Speech-to-text	4 Feb 2026	—	—	—
Qwen3-ASR (open)Qwen-ASR · Open weights	Alibaba Group	Speech-to-text	29 Jan 2026	—	—	—
VibeVoice-ASRVibeVoice ASR · Open weights	Microsoft	Speech-to-text	21 Jan 2026	—	—	—
Nemotron Speech Streaming EN 0.6BNemotron Speech (ASR) · Legacy · Open weights	NVIDIA	Speech-to-text	17 Dec 2025	—	—	—
Fun-ASR-Nano-2512FunAudioLLM · Open weights	Alibaba Group	Speech-to-text	15 Dec 2025	—	—	—
GLM-ASR-2512GLM-ASR · Open weights	Z.ai (Zhipu AI)	Speech-to-text	10 Dec 2025	—	—	—
Deepgram Flux (English, Multilingual)Deepgram speech-to-text (Base, Enhanced, Nova, Flux)	Deepgram	Speech-to-text	Oct 2025	—	—	—
Qwen3-Omni-30B-A3B-CaptionerQwen-Audio · Open weights	Alibaba Group	Speech-to-text	22 Sep 2025	—	$3.81	$3.06
Qwen3-ASR-FlashQwen-ASR · Legacy	Alibaba Group	Speech-to-text	8 Sep 2025	—	—	—
Chirp 3Chirp	Google	Speech-to-text	29 Aug 2025	—	—	—
Fun-ASRFunAudioLLM	Alibaba Group	Speech-to-text	25 Aug 2025	—	—	—
Canary 1B v2Canary · Open weights	NVIDIA	Speech-to-text	4 Aug 2025	—	—	—
Parakeet TDT 0.6B v3Parakeet · Open weights	NVIDIA	Speech-to-text	4 Aug 2025	—	—	—
OLMoASROLMoASR · Open weights	Allen Institute for AI (Ai2)	Speech-to-text	Aug 2025	—	—	—
Canary-Qwen 2.5BCanary · Open weights	NVIDIA	Speech-to-text	26 Jun 2025	—	—	—
Parakeet TDT 0.6B v2Parakeet · Legacy · Open weights	NVIDIA	Speech-to-text	15 Apr 2025	—	—	—
Granite Speech 3.3 (2B, 8B)Granite Speech · Legacy · Open weights	IBM	Speech-to-text	Apr 2025	—	—	—
Granite Speech 3.2 8BGranite Speech · Legacy · Open weights	IBM	Speech-to-text	26 Mar 2025	—	—	—
GPT-4o mini TranscribeGPT transcription models · Deprecated	OpenAI	Speech-to-text	20 Mar 2025	16K	$1.25	$5.00
GPT-4o TranscribeGPT transcription models · Deprecated	OpenAI	Speech-to-text	20 Mar 2025	16K	$2.50	$10.00
Canary 1B FlashCanary · Legacy · Open weights	NVIDIA	Speech-to-text	7 Mar 2025	—	—	—
Deepgram Nova-3Deepgram speech-to-text (Base, Enhanced, Nova, Flux)	Deepgram	Speech-to-text	Feb 2025	—	—	—
Whisper large-v3-turboWhisper · Open weights	OpenAI	Speech-to-text	30 Sep 2024	—	—	—
Qwen2-Audio-7B-InstructQwen-Audio · Legacy · Open weights	Alibaba Group	Speech-to-text	9 Aug 2024	8.2K	—	—
SenseVoice-SmallFunAudioLLM · Legacy · Open weights	Alibaba Group	Speech-to-text	Jul 2024	—	—	—
Canary 1BCanary · Legacy · Open weights	NVIDIA	Speech-to-text	7 Feb 2024	—	—	—
Parakeet TDT 1.1BParakeet · Legacy · Open weights	NVIDIA	Speech-to-text	25 Jan 2024	—	—	—
Parakeet CTC / RNNT 1.1BParakeet · Legacy · Open weights	NVIDIA	Speech-to-text	28 Dec 2023	—	—	—
Qwen-Audio-ChatQwen-Audio · Legacy · Open weights	Alibaba Group	Speech-to-text	30 Nov 2023	2K	—	—