whisper-base
Last updated
Was this helpful?
Last updated
Was this helpful?
Note:
Previously, our STT models operated via a single API call to POST https://api.aimlapi.com/v1/stt
. You can view the API schema .
Now, we are switching to a new two-step process:
POST https://api.aimlapi.com/v1/stt/create
– Creates and submits a speech-to-text processing task to the server. This method accepts the same parameters as the old version but returns a generation_id
instead of the final transcript.
GET https://api.aimlapi.com/v1/stt/{generation_id}
– Retrieves the generated transcript from the server using the generation_id
obtained from the previous API call.
This approach helps prevent generation failures due to timeouts. We've prepared below to make the transition to the new STT API easier for you.
The Whisper models are primarily for AI research, focusing on model robustness, generalization, and biases, and are also effective for English speech recognition. The use of Whisper models for transcribing non-consensual recordings or in high-risk decision-making contexts is strongly discouraged due to potential inaccuracies and ethical concerns.
The models are trained using 680,000 hours of audio and corresponding transcripts from the internet, with 65% being English audio and transcripts, 18% non-English audio with English transcripts, and 17% non-English audio with matching non-English transcripts, covering 98 languages in total.
Whisper models use per-second billing. The cost of audio transcription is based on the number of seconds in the input audio file, not the processing time.
If you don’t have an API key for the AI/ML API yet, feel free to use our .
Let's use the #g1_whisper-base
model to transcribe the following audio fragment:
A custom intent you want the model to detect within your input audio if present. Submit up to 100.
A custom topic you want the model to detect within your input audio if present. Submit up to 100.
Sets how the model will interpret strings submitted to the custom_intent param. When strict, the model will only return intents submitted using the custom_intent param. When extended, the model will return its own detected intents in addition those submitted using the custom_intents param.
Sets how the model will interpret strings submitted to the custom_topic param. When strict, the model will only return topics submitted using the custom_topic param. When extended, the model will return its own detected topics in addition to those submitted using the custom_topic param.
Enables language detection to identify the dominant language spoken in the submitted audio.
When Entity Detection is enabled, the Punctuation feature will be enabled by default.
Detects the most important and relevant topics that are referenced in speech within the audio
Recognizes speaker changes. Each word in the transcript will be assigned a speaker number starting at 0
Identifies and extracts key entities from content in submitted audio
Arbitrary key-value pairs that are attached to the API response for usage in downstream processing
Filler Words can help transcribe interruptions in your audio, like “uh” and “um”
Recognizes speaker intent throughout a transcript or text
Keywords can boost or suppress specialized terminology and brands
The BCP-47 language tag that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available
Spoken measurements will be converted to their corresponding abbreviations
Transcribes each audio channel independently
Numerals converts numbers from written format to numerical format
Splits audio into paragraphs to improve transcript readability
Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely
Adds punctuation and capitalization to the transcript
Search for terms or phrases in submitted audio
Recognizes the sentiment throughout a transcript or text
Applies formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability
Summarizes content. For Listen API, supports string version option. For Read API, accepts boolean only.
Labels your requests for the purpose of identification during usage reporting
Detects topics throughout a transcript or text
Segments speech into meaningful semantic units
Seconds to wait before detecting a pause between words in submitted audio