Speech to Text
About Microsoft Speech to Text
Speech Recognition (or speech to text or voice to text) can recognize and transcribe spoken words (voice), that will be converted to text with or without diarization. It is also possible to filter profanity. The type of files allowed are: mp3, wav, m4a. If convert_to_wav option is set to true, then you can transcribe any type of audio or video files.
Microsoft Speech to Text is Microsoft's default model for Speech to Text available on Eden AI for Speech to Text, from $0.0168 / min. Call it with the same API key as every other Eden AI model by sending its model string to the Universal AI endpoint, with processing in Europe.
Tasks and prices
Microsoft Speech to Text is available on Eden AI for 1 tasks. Each task has its own model string and price: send that string to the Universal AI endpoint to use the model for that task.
Parameters
What you send and what you get back when you call Microsoft Speech to Text through Eden AI. The same fields work with every model of the same task, so you can switch model without changing your code.
Input
- file (required): file (audio). Audio file ID from /v3/upload or direct file URL
- language: text. Language code in ISO format (e.g., 'en', 'fr', 'es')
- speakers: number. Number of speakers present in the audio
- profanity_filter: true / false. Whether to filter profanity and replace inappropriate words with a series of asterisks
- vocabulary: list. List of words or composed words to be detected by the speech to text engine
Response
- text
- diarization
Estimate your monthly cost
Enter your monthly volume for Speech to Text to compare Microsoft Speech to Text with its cheapest alternatives.
Call Microsoft Speech to Text with Eden AI
Send the model string to the Universal AI endpoint. To use another model, copy its string from the table above.
import requests
response = requests.post(
"https://api.edenai.run/v3/universal-ai",
headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
json={
"model": "",
"input": {},
},
)
print(response.json())
curl https://api.edenai.run/v3/universal-ai \
-H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "", "input": {}}'
const response = await fetch("https://api.edenai.run/v3/universal-ai", {
method: "POST",
headers: {
Authorization: "Bearer YOUR_EDENAI_API_KEY",
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "",
input: {},
}),
});
console.log(await response.json());
"file": "https://example.com/audio.mp3"
Questions about Microsoft Speech to Text
On Eden AI, Microsoft Speech to Text costs $0.0168 / min for Speech to Text. The Tasks and prices table lists the price for each task, and you only pay for what you use.
On Eden AI, Microsoft Speech to Text is available for: Speech to Text. Input: Audio. Output: text, diarization.
Yes. Microsoft Speech to Text is processed in Europe for at least one task: see the Regions column in the Tasks and prices table.
Asynchronous: you start a job, then get the result by polling it or through a webhook. This suits long files such as audio, video or multipage documents.
Eden AI offers Speech to Text from 9 providers, all callable with the same API key. The cheapest models are compared just below.
Alternatives for Speech to Text
Other Speech to Text models you can call with the same key, cheapest first.
More from Microsoft
Other Microsoft models on Eden AI, for every task.
.avif)
