WaveSpeed.ai
Startseite/Entdecken/OpenAI Models/wavespeed-ai/openai-whisper-turbo
speech-to-text

speech-to-text

OpenAI Whisper Large V3 Turbo

wavespeed-ai/openai-whisper-turbo

Accurate speech-to-text with OpenAI Whisper Large v3 Turbo: multilingual transcripts with auto language detection and punctuation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input

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

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": "Welcome to WaveSpeed AI."
}

Ihre Anfrage kostet $0.0007 pro Durchlauf.

Für $1 können Sie dieses Modell ungefähr 1428 Mal ausführen.

BeispieleAlle anzeigen

README

OpenAI Whisper Turbo

OpenAI Whisper Turbo is a fast, accurate speech-to-text transcription model powered by OpenAI's Whisper architecture. It converts audio into clean, readable text with support for multiple languages — ideal for transcription, subtitling, and voice-driven workflows.

Why It Stands Out

  • High-speed transcription: Optimized for fast processing without sacrificing accuracy.
  • Multilingual support: Transcribe audio in dozens of languages with automatic language detection.
  • Prompt-guided transcription: Steer output formatting, terminology, or punctuation with custom prompts.
  • Prompt Enhancer: Built-in AI-powered prompt optimization for better transcription guidance.
  • Flexible input: Supports direct audio upload or public URL.

Parameters

ParameterRequiredDescription
audioYesUpload or link to an audio file (MP3 / WAV / M4A, etc.).
languageNoLanguage code for transcription; leave empty for auto-detection.
promptNoShort guidance text to steer transcription style or terminology.
enable_sync_modeNoWait for result before returning response (API only).

How to Use

  1. Upload your audio — drag and drop a file or paste a public URL.
  2. Select language (optional) — choose a specific language or let the model auto-detect.
  3. Add a prompt (optional) — guide formatting, punctuation, or specific terminology.
  4. Click Run and wait for transcription to complete.
  5. Copy or download the transcribed text.

Best Use Cases

  • Meeting Transcription — Convert recorded meetings, interviews, and calls into searchable text.
  • Subtitle Generation — Create accurate transcripts for video subtitling workflows.
  • Content Repurposing — Turn podcasts, webinars, and lectures into written content.
  • Voice Notes — Quickly transcribe voice memos and audio notes.
  • Accessibility — Generate transcripts to make audio content accessible.

Pricing

MetricPrice
Per second of audio$0.0007 / s

Total cost = duration of audio (in seconds) × $0.0007

Examples

  • 60s audio → 60 × $0.0007 = $0.042
  • 5 min (300s) audio → 300 × $0.0007 = $0.21
  • 30 min (1800s) audio → 1800 × $0.0007 = $1.26

Pro Tips for Best Quality

  • Use clear audio with minimal background noise for optimal accuracy.
  • Specify the language if auto-detection is inconsistent.
  • Add a prompt to guide transcription — include names, jargon, or formatting preferences.
  • For long recordings, consider splitting into smaller segments for faster processing.

Notes

  • Ensure uploaded audio URLs are publicly accessible.
  • Processing time varies based on audio duration and current queue load.