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

Parameter	Required	Description
audio	Yes	Upload or link to an audio file (MP3 / WAV / M4A, etc.).
language	No	Language code for transcription; leave empty for auto-detection.
prompt	No	Short guidance text to steer transcription style or terminology.
enable_sync_mode	No	Wait for result before returning response (API only).

How to Use

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

Metric	Price
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.

Openai Whisper Turbo API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/openai-whisper with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Openai Whisper Turbo below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/openai-whisper" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "audio": "https://example.com/your-audio.mp3",
    "language": "auto",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "enable_sync_mode": false
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("wavespeed-ai/openai-whisper-turbo", {
        "audio": "https://example.com/your-audio.mp3",
        "language": "auto",
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "enable_sync_mode": false
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/openai-whisper-turbo",
    {
    "audio": "https://example.com/your-audio.mp3",
    "language": "auto",
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "enable_sync_mode": false
}
)

print(output["outputs"][0])  # → URL of the generated output

Openai Whisper Turbo API — Frequently asked questions

What is the Openai Whisper Turbo API?

Openai Whisper Turbo is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. 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. You can call it programmatically or try it from the playground above.

How do I call the Openai Whisper Turbo API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/openai-whisper-turbo.

How much does Openai Whisper Turbo cost per run?

Openai Whisper Turbo starts at $0.001 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Openai Whisper Turbo accept?

Key inputs: `prompt`, `audio`, `enable_sync_mode`, `language`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/openai-whisper-turbo.

How long does Openai Whisper Turbo take to generate?

Average end-to-end generation time on WaveSpeedAI is around 12 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Openai Whisper Turbo outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ตัวอย่างดูทั้งหมด

โมเดลที่เกี่ยวข้อง

README