Speech-to-text APIs

• 3of 50

  run on Mac

• 2of 50

  run on Windows

• 2of 50

  run on Linux

• 3of 50

  on iPhone or iPad

• 2of 50

  on Android

• 3of 50

  say speech stays on the device

Counted from the 50 entries below, as each maker's own pages list them.

All 50

• ElevenLabs Scribe

  ElevenLabs · API

  ElevenLabs' speech-to-text models and API for transcribing recorded and live audio in many languages.

  • $0.22 an hour of audio, Scribe v2 Medical
  • 3,970,853 SDK downloads a month
  • 90 languages
• Mistral Voxtral Transcribe

  Mistral AI · API

  Mistral AI's speech-to-text API, powered by its Voxtral models, for transcribing recorded and live audio.

  • $0.18 an hour of audio, Voxtral Mini Transcribe V2
  • 32,317,341 SDK downloads a month
  • 13 languages
• OpenAI Speech to Text API

  OpenAI · API

  OpenAI's speech-to-text API for developers, which transcribes recorded audio files and live audio into text.

  • 175,958,798 SDK downloads a month
• Deepgram

  Deepgram · API

  A voice AI platform whose speech-to-text APIs developers use to transcribe live and recorded audio.

  • $0.39 an hour of audio, Flux English
  • 4,092,784 SDK downloads a month
  • 60 languages
• AssemblyAI

  AssemblyAI · API

  A speech AI company whose API transcribes recorded and live audio for developers building voice products.

  • $0.3 an hour of audio, Sync API (Universal-3.5 Pro)
  • 2,280,177 SDK downloads a month
  • 99 languages
• Speechmatics

  Speechmatics · API, Self-hosted

  A speech recognition company whose APIs transcribe live and recorded audio in many languages, with cloud and on-premises deployment options.

  • 119,664 SDK downloads a month
  • 55 languages
• Amazon Transcribe

  Amazon Web Services · API

  An Amazon Web Services speech recognition service that converts audio from files and live streams into text, for developers and businesses.

  • $0.36 an hour of audio, Amazon Transcribe
  • 1,277,058 SDK downloads a month
  • 100 languages
• Soniox

  Soniox · API

  A speech AI platform whose API transcribes live and recorded audio in many languages.

  • $0.1 an hour of audio, Speech-to-Text async (file uploads)
  • 102,409 SDK downloads a month
• Rev AI

  Rev · API

  Rev's speech-to-text API that developers use to transcribe recorded and live audio.

  • $0.3 an hour of audio, Reverb Foreign Language Transcription
  • 55,905 SDK downloads a month
• Gladia

  Gladia · API

  An audio transcription API for developers building voice products, covering recorded and live audio.

  • 18,223 SDK downloads a month
• Google Cloud Speech-to-Text

  Google Cloud · API

  A Google Cloud service that converts speech from audio files and live streams into text through an API, for developers and businesses.

  • $0.18 an hour of audio, Dynamic batch (standard models)
  • 2,831,975 SDK downloads a month
  • 125 languages
• GroqCloud Speech to Text

  Groq · API

  GroqCloud's speech-to-text API, which runs Whisper models on Groq's inference hardware for developers.

  • $0.111 an hour of audio, whisper-large-v3
  • 3,810,140 SDK downloads a month
• Azure AI Speech

  Microsoft · API

  Microsoft's Azure speech service, which converts speech to text in real time or in batch through APIs and SDKs for developers.

  • 7,713 SDK downloads a month
• Fireworks AI audio transcription

  Fireworks AI · API

  Fireworks AI's audio transcription API, which serves Whisper-based models for transcribing files and live audio.

  • $0.09 an hour of audio, Whisper v3 large
  • 1,157,786 SDK downloads a month
• Gemini API transcription

  Google · API

  Speech-to-text models in Google's Gemini API that transcribe live audio streams and recorded audio for developers building voice interfaces.

  • 102,468,836 SDK downloads a month
• Picovoice Cheetah

  Picovoice · Mac, Windows, Linux, iPhone, Android

  An on-device streaming speech-to-text engine from Picovoice that transcribes live speech inside apps without sending it to the cloud.

  • 518 SDK downloads a month
• Picovoice Leopard

  Picovoice · Mac, Windows, Linux, iPhone, Android

  An on-device speech-to-text engine from Picovoice that transcribes recorded audio inside apps without sending it to the cloud.

  • 843 SDK downloads a month
• Smallest.ai Pulse

  Smallest.ai · API

  Pulse is Smallest.ai's speech-to-text model for live and recorded audio, offered through APIs and SDKs for voice agents, captions and call analytics.

• Baidu Speech Recognition

  Baidu · API

  Baidu AI Cloud's speech recognition service, which converts speech to text through APIs and SDKs.

  • 6,135 SDK downloads a month
• Cartesia Ink

  Cartesia · API

  Cartesia's Ink streaming speech-to-text models for production voice agents, with built-in turn detection.

  • 459,483 SDK downloads a month
• Cloudflare Workers AI speech-to-text

  Cloudflare · API

  Cloudflare Workers AI's hosted Whisper speech-to-text models, called from Workers or the REST API.

  • 13,493,182 SDK downloads a month
• fal speech-to-text

  fal · API

  fal's hosted speech-to-text models, including Whisper, available through an API for developers.

  • 6,817,609 SDK downloads a month
• Grok Speech to Text

  SpaceXSI (xAI) · API

  A speech-to-text API for transcribing audio files and live audio streams, offered by the maker of the Grok models.

  • 4,773,444 SDK downloads a month
• IBM Watson Speech to Text

  IBM · API

  IBM's cloud speech recognition service that transcribes audio into text through an API, for developers and enterprises.

  • 44,739 SDK downloads a month
• Microsoft MAI-Transcribe

  Microsoft AI · API

  A speech-to-text model built by the Microsoft AI team, available through the Azure Speech API for transcribing recorded audio such as meetings and calls.

• Oracle Cloud Infrastructure Speech

  Oracle · API

  Oracle Cloud Infrastructure's speech service, which converts audio files to text through an API.

  • 473,238 SDK downloads a month
• Replicate speech-to-text models

  Replicate · API

  Replicate's hosted Whisper and other speech-to-text models that developers run through an API.

  • 2,470,241 SDK downloads a month
• Reson8

  Resonate Labs · API, Self-hosted

  Reson8 is a speech-to-text API for regulated industries and voice agent builders, aimed at accurate transcription of domain-specific terms.

• Sarvam Speech to Text

  Sarvam · API

  Sarvam's speech-to-text API for transcribing Indian languages and Indian English, for developers and enterprises.

  • 45,373 SDK downloads a month
• Telnyx Speech-to-Text API

  Telnyx · API

  Telnyx's speech-to-text API, which gives developers access to several speech engines through one integration for voice agents and captions.

  • 1,582,453 SDK downloads a month
• Tencent Cloud ASR

  Tencent Cloud · API

  Tencent Cloud's automatic speech recognition service, which turns audio into text through APIs and SDKs.

  • 7,910 SDK downloads a month
• Together AI audio transcription

  Together AI · API

  Together AI's speech-to-text API, which transcribes audio files with hosted speech models for developers.

  • 413,434 SDK downloads a month
• Alibaba Cloud Model Studio speech recognition

  Alibaba Cloud · API

  Alibaba Cloud Model Studio's speech-to-text models and APIs for transcribing recorded and live audio.

  • 2,487,885 SDK downloads a month
• Gradium Speech-to-Text

  Gradium · API

  Gradium's real-time speech-to-text model and API for voice agent builders.

• Meta Muse Voice Transcribe

  Meta · API

  Meta's real-time speech-to-text model, offered to developers through the Meta Model API.

• Modulate Velma Transcribe

  Modulate · API

  Modulate's speech-to-text API for batch and real-time transcription of conversational audio.

• AmiVoice API

  Advanced Media · API

  AmiVoice Cloud Platform is Advanced Media's speech recognition API and SDK for developers.

• Apple SpeechAnalyzer

  Apple · Mac, iPhone, iPad

  Apple's speech-to-text framework for apps on Mac, iPhone and iPad, exposed to developers through the SpeechAnalyzer API.

• DeepInfra speech-to-text

  DeepInfra · API

  DeepInfra's hosted speech-to-text models, including Whisper, available through an API for developers.

• iFlytek Speech Recognition

  iFlytek · API

  iFlytek's speech recognition service on its open platform, which converts speech to text through APIs.

• Lemonfox.ai Speech-to-Text API

  Lemonfox.ai · API

  Lemonfox.ai is a speech-to-text API for developers, built on Whisper.

• NAVER CLOVA Speech

  NAVER Cloud · API

  CLOVA Speech is a speech recognition service listed among the AI services of NAVER Cloud Platform.

• Phonexia Speech to Text

  Phonexia · API, Self-hosted

  Phonexia's speech-to-text technology, built for on-premises and private-cloud deployments.

• RTZR STT API

  ReturnZero · API

  ReturnZero's speech-to-text API for real-time streaming and audio-file transcription, including speaker diarization and keyword boosting.

• Salad Transcription API

  Salad Technologies · API

  Salad's transcription API converts audio to text with options such as translation and speaker identification, for teams transcribing audio in bulk.

• SaluteSpeech

  Sber · API

  Sber's speech recognition and synthesis API for developers building voice assistants and call analysis.

• Vatis Tech

  Vatis Tech · Web, API

  Vatis Tech offers a speech-to-text API and web app for transcribing audio and video.

• Vocapia VoxSigma

  Vocapia · API

  VoxSigma is Vocapia's multilingual speech-to-text suite for transcribing broadcast, video and call-center audio.

• Voicegain

  Voicegain · API, Self-hosted

  Voicegain offers speech-to-text APIs and an AI voice agent platform, with cloud and on-premises deployment options.

• Web Speech API

  W3C Web Speech API Community Group · Web, Chrome, Edge, Safari

  A browser API that lets web pages recognize speech and turn it into text.