whisper-1 is OpenAI's speech-to-text model, corresponding to Whisper large-v2 at the time of the official API release. It is suitable for organizing speech from interviews, courses, voice messages, and audio-visual materials into original-language text, with text, JSON, or subtitle formats selected according to the workflow. On this platform, you can submit files through the audio transcription entry point to integrate recording processing into content production and document organization workflows.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
api.acedata.cloudwhisper-1Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Clarify capacity, inputs and outputs, and calling methods before selecting a model.
Native format details and call parameters are listed separately; this entry point focuses on file transcription and is not equivalent to real-time voice conversation.
Learn what whisper-1 can bring to your work.
whisper-1's transcription task converts spoken audio into original-language text rather than translating it into English by default. This is suitable for interviews, courses, and dictated materials where original wording needs to be preserved. The generated text can serve as a basis for subsequent search, excerpting, and editing, while summarization and rewriting should be handled as separate processing steps.
The same transcription workflow can select output formats based on use: text is suitable for direct entry into an editor, JSON makes text easier for programs to read, and SRT and VTT are suitable for subtitle production. Format selection should be designed around the final deliverable to avoid first saving plain text and then separately rebuilding subtitle structure and processing workflows.
Calls center on audio files, so recordings do not need to be converted into chat messages. Requests can include language and prompt text to help applications organize transcription context; prompts should be prepared around the recording content rather than treated as free-form creative instructions. This makes it easier to connect uploading, transcription, saving, and manual proofreading into a stable workflow.
Start with specific tasks to identify where the model can be useful.
Submit interview recordings or oral materials as files, choose text or JSON output, and receive transcripts that are easy to search and edit. Editors can use them to locate topics, organize quotations, and listen back to verify names, organization names, and key original statements; article structure and insight extraction can be handled separately after transcription is complete.
Choose SRT or VTT output for course recordings or video materials, then send the results into a subtitle editing or playback workflow. Before delivery, check sentence breaks and the correspondence between text and timing against the original material; the model handles speech transcription, while subtitle layout, visual styling, and final video export are still completed by production tools.
Convert user voice messages into text for storage in ticketing systems or knowledge bases. Applications can read the text in JSON and associate the transcription with the original audio, making it easier for staff to review and listen back. Classification, priority assessment, and response generation should be handled in separate processing steps rather than treating transcription results directly as business decisions.
Choose based on task complexity, input materials, and expected results.
If the core requirement is to process existing recordings and deliver original-language text or subtitles, whisper-1 has a clear task boundary. It is neither a general question-answering model nor a speech synthesis model: it will not read text aloud as audio, nor should it be expected to handle all of the work of automatically writing meeting notes. Complete transcription first, then follow with summarization or editing workflows for easier verification against the original speech.
whisper-1 is the API call name, while large-v2 is the corresponding native version from the official release; it should not be understood as a blanket term for all newer Whisper versions. When comparing other transcription models, use the same recording to check proper nouns, sentence breaks, and required output formats; if the goal is English translation, also distinguish between transcription in the original language and a separate translation task.
Arrange the input first, then connect it to the appropriate application workflow.
Prepare the interview audio and correct proper nouns, and specify whether the output should be an original-language transcription or subtitles.
Upload the binary file through /v1/audio/transcriptions and explicitly select whisper-1; first obtain the basic text result, then choose verified subtitle or timing information output as needed for the task. Keep the original recording available for playback during editing.
Design the task directly from the following inputs and acceptance priorities.
Upload audio using file, with model=whisper-1; when subtitles are needed, select the corresponding srt or vtt format in the documentation, and include language and terminology prompts.
Verify text, sentence breaks, and timing alignment in the player, and listen again to overlapping speech from multiple speakers; file transcription cannot be directly equated with real-time voice conversations.
Before formal use, understand the output quality and scope of capabilities.
Answers to common questions about using whisper-1.
whisper-1 is the model name used when calling the API, and OpenAI's Whisper API release notes map it to large-v2. They describe the invocation name and the native version respectively. whisper-1 should not be treated as a generic alias for all Whisper versions, nor should this be taken to mean it is the latest version.
The audio transcription endpoint outputs text in the original language; it does not translate to English by default. The official documentation distinguishes transcription in the original language from translation into English as separate tasks. Therefore, Chinese recordings should be processed using the Chinese transcription workflow; if an English transcript is needed, a separate translation step should be arranged.
The API parameters provide srt and vtt output options for subtitle workflows; for plain-text tasks, text or json can be selected. After subtitles are generated, the content, line breaks, and timing should still be checked against the audio before handing them to subtitle editing or playback tools; they should not be considered a finished production directly.
prompt is hint text in a transcription request and should not be treated as a general-purpose writing instruction. The core deliverable of whisper-1 remains an audio transcript. If an article, summary, or action items are needed, it is recommended to preserve the original transcription result and then pass it to a separate text-processing step, avoiding confusion between the original words and processed content.
When calling /v1/audio/transcriptions directly, you need to submit a binary file and use whisper-1. If using an MCP client, you can choose its tool for transcribing audio from a URL. The input organization differs between the two approaches; do not pass a URL string directly as HTTP's binary file field.
Choose a development approach or application suited to this model and follow its setup guide.
↗Python SDK Integration Guide
SDK installation, authentication and examples↗TypeScript SDK Integration Guide
SDK installation, authentication and examples
↗Pricing
$0.0001· per second
You pay$13,584for 142,800 credits · $0.0951 / credits46% OFF
You're billed in credits. Pick a top-up tier to see its per-credit rate — the larger the top-up, the cheaper each credit.
This is only a basic call example. See the full docs for more parameters and advanced usage.
View Docs