Audio Intelligence

Deploy Powerful Transcription and Audio Intelligence in 97 Languages
// Transcribe, process and analyze audio and video with our powerful Whisper-based Audio Intelligence solution.
Access cutting-edge AI models for transcription, speaker identification, sentiment analysis, topic detection, and more - all with a single API call.
Pricing

Whisper+

// Trained on 680,000 hours of multilingual and multitask data, the Whisper model has been designed to effectively transcribe challenging forms of speech including whispering, hushed or low-volume speech, various accents, technical language, and background noise.

Whisper+ is our extension of the Whisper model, which adds powerful features such as speaker identification and custom vocabulary, and supports our audio intelligence capabilities, including summarization and chapter generation.

Compare

Whisper

Whisper+

Int.

Analytics

Enhanced Model
Supported languages
Info
97
97
97
97
Language detection
Info
-
Speaker diarization & identification
Info
-
Custom vocabulary & spelling
Info
-
Punctuation
Info
-
Filler word removal
Info
-
Number standardization
Info
-
Detect key words & phrases
Info
-
PII redaction
Info
-
Split to sentences
Info
-
Summarization
Info
-
-
Summary to source alignment
Info
-
-
Chapter generation
Info
-
-
Topic extraction
Info
-
-
Emotions & sentiment analysis
Info
-
-
Named entity recognition
Info
-
-
Custom Skill integration
Info
-
-
Large scale language analytics
Info
-
-
-

Soniox

$0.4

/Hour
World-leading speech-to-text in latency and scalability, with a 95% speech-to-text accuracy rate
  • Automatically convert audio and video files into text
  • Instant voice recognition of spoken words with high accuracy
  • 40% more accurate than any other provider
  • Lower latency than any other provider
  • Customizable vocabulary
  • Effectively recognizes domain-specific words
  • Expeditious and accurate results
  • Processes, analyzes, and converts large audio and video files within minutes

Integrate in Minutes

import oneai oneai.api_key = "CLICK_TO_GET_YOUR_API_KEY" pipeline = oneai.Pipeline(steps=[ oneai.skills.Transcribe(speaker_detection=True), oneai.skills.Chapters(), oneai.skills.Summarize(), ]) with open("example.mp3", "rb") as inputf: output = pipeline.run(inputf) print(output)
Copy
import OneAI from 'oneai'; const oneai = new OneAI({apiKey: 'CLICK_TO_GET_YOUR_API_KEY'}); const pipeline = new oneai.Pipeline( oneai.skills.transcribe(speaker_detection=true), oneai.skills.chapters(), oneai.skills.summarize(), ); const output = await pipeline.runFile('example.mp3'); console.log(output);
Copy
curl -X POST \ 'https://api.oneai.com/api/v0/pipeline/async/file?pipeline=%7B%22input_type%22%3A%22dialog%22%2C%22steps%22%3A%5B%7B%22skill%22%3A%22transcribe%22%2C%22params%22%3A%7B%22speaker_detection%22%3Atrue%7D%7D%5D%2C%22content_type%22%3A%22audio%2Fwav%22%7D' \ -H 'accept: application/json' \ -H 'Content-Type: application/json' \ -H 'api-key: CLICK_TO_GET_YOUR_API_KEY' \ --upload-file "example.mp3" curl -X GET \ 'https://api.oneai.com/api/v0/pipeline/async/tasks/TASK_ID_FROM_PREVIOUS_STEP' \ -H 'accept: application/json' \ -H 'api-key: 07ea922e-3bfd-4544-a8d7-730462c528e6' \
Copy
Studio