Openai Whisper

Playground

Instant, accurate speech-to-text powered by Whisper large-v3-turbo. Upload audio and receive multilingual transcripts with automatic language detection and punctuation.

Features

OpenAI Whisper Speech-to-Text

WaveSpeed’s Whisper deployment delivers production-ready speech recognition built on the large-v3 checkpoint. Upload audio (MP3, WAV, FLAC) and receive accurate transcripts with automatic language detection.

Highlights

Multilingual recognition across 50+ languages
Automatic punctuation and casing
Robust to background noise and accents
Runs on GPU-accelerated infrastructure for fast turnaround

Quick Start

Provide an audio file or HTTPS URL in the “audio” field.
Submit the request via API or dashboard.
Receive a JSON response containing the transcribed text.

Example output:

&#123;
  "outputs": &#123;
    "text": "Hello everyone, welcome to the show."
  &#125;
&#125;

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/openai-whisper" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "language": "Auto",
    "task": "transcribe",
    "enable_timestamps": false,
    "prompt": "",
    "enable_sync_mode": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
audio	string	Yes	-	-	Audio file to transcribe. Provide an HTTPS URL or upload a file (MP3, WAV, FLAC up to 60 minutes).
language	string	No	Auto	Afrikaans, Amharic, Arabic, Assamese, Azerbaijani, Bashkir, Belarusian, Bulgarian, Bengali, Tibetan, Breton, Bosnian, Catalan, Czech, Welsh, Danish, German, Greek, English, Spanish, Estonian, Basque, Persian, Finnish, Faroese, French, Galician, Gujarati, Hausa, Hawaiian, Hebrew, Hindi, Croatian, Haitian Creole, Hungarian, Armenian, Indonesian, Icelandic, Italian, Japanese, Javanese, Georgian, Kazakh, Khmer, Kannada, Korean, Latin, Luxembourgish, Lingala, Lao, Lithuanian, Latvian, Malagasy, Maori, Macedonian, Malayalam, Mongolian, Marathi, Malay, Maltese, Myanmar, Nepali, Dutch, Nynorsk, Norwegian, Occitan, Punjabi, Polish, Pashto, Portuguese, Romanian, Russian, Sanskrit, Sindhi, Sinhala, Slovak, Slovenian, Shona, Somali, Albanian, Serbian, Sundanese, Swedish, Swahili, Tamil, Telugu, Tajik, Thai, Turkmen, Tagalog, Turkish, Tatar, Ukrainian, Urdu, Uzbek, Vietnamese, Yiddish, Yoruba, Chinese, Cantonese, Auto	Language spoken in the audio. Set to 'auto' for automatic language detection (default).
task	string	No	transcribe	transcribe, translate	The task to perform. 'transcribe' to the source language or 'translate' to English.
enable_timestamps	boolean	No	false	-	Enable to generate word-level timestamps for the transcription. Note: This may increase processing time.
prompt	string	No		-	An optional text to provide as a prompt to guide the model's style or continue a previous audio segment. The prompt should be in the same language as the audio.
enable_sync_mode	boolean	No	true	-	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.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Neta Lumina Openai Whisper Turbo