bannerbannerExperience Now
WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/OpenAI Models/wavespeed-ai/openai-whisper
speech-to-text

speech-to-text

OpenAI Whisper Large V3 | Multilingual Speech To Text With Auto Language Detection | WaveSpeedAI

wavespeed-ai/openai-whisper

Whisper Large v3 speech-to-text: instant, accurate multilingual transcripts with automatic language detection and punctuation. Upload audio to get transcripts. Ready-to-use REST API, no coldstarts, affordable pricing.

Hint: You can drag and drop a file or click to upload

Enable to generate word-level timestamps for the transcription. Note: This may increase processing time.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

{
  "text": "Bir ses bin duyguyu anlatabilir ve her kelime bir kalbe dokunabilir."
}

Your request will cost $0.001 per run.

For $1 you can run this model approximately 1000 times.

ExamplesView all

README

OpenAI Whisper — Speech-to-Text

WaveSpeedAI’s Whisper deployment provides high-accuracy, production-ready speech recognition powered by OpenAI’s large-v3 model. It converts audio (MP3, WAV, FLAC) into precise, punctuated text with automatic language detection and multilingual support.

⚡ Highlights

  • Multilingual Recognition — supports over 50 languages including English, Chinese, French, Japanese, and more.
  • Accurate Punctuation & Capitalization — automatically generates clean, well-formatted text.
  • Noise Robustness — performs reliably in diverse environments and accent variations.
  • GPU-Optimized — fast and efficient transcription for real-world production workloads.

💰 Pricing

  • Basic Service (No Timestamp)

    • $0.001 per second

  • Advanced Service (With Timestamp)

    • $0.002 per second

🚀 Quick Start

  1. Upload your audio file (.mp3, .wav, .flac) or provide a valid HTTPS link.
  2. Choose between Basic or Advanced transcription modes.
  3. (Optional) Specify language manually, or leave Auto for automatic detection.
  4. Submit the request and receive your transcript in JSON format.

Example output:

{
  "outputs": {
    "text": "Hello everyone, welcome to the show."
  }
}

📝 Notes

  • The Advanced Service provides timestamped segments for subtitles and detailed analysis.
  • For long audio (>10 minutes), split into segments for optimal accuracy and speed.
  • The model automatically handles punctuation, casing, and accent variations.
  • Supported formats: MP3, WAV, FLAC, M4A.