TAAFT
Free mode
100% free
Freemium
Free Trial
Prompts Deals
Companies
OpenAI
Models
Whisper

Whisper

By OpenAI
Whisper is an open-source speech model family built for multilingual automatic speech recognition, speech translation into English, and spoken language identification. The repository describes it as a general-purpose multitask Transformer seq2seq model trained on a large and diverse audio dataset, using special task tokens so one model can handle several speech-processing tasks in a unified framework. The current repo lists six size tiers, from 39M-parameter tiny models up to 1.55B-parameter large, plus a turbo model optimized from large-v3 for faster transcription with only a small accuracy tradeoff.
Multimodal
Released: September 21, 2022

Overview

Whisper is OpenAI’s open-source general-purpose speech recognition model for transcription, translation, and language identification. It is a multitask Transformer sequence-to-sequence system trained on large-scale diverse audio, with multilingual support and model sizes ranging from tiny to large plus a faster turbo variant.

🗒Transcription🎙️Voice recognition🎧Audio translation🌍Multilingual subtitle creation

About OpenAI

OpenAI is a technology company that specializes in artificial intelligence research and innovation.

Industry: Artificial Intelligence
Company Size: 4500
Location: San Francisco, California, US
Website: openai.com
View Company Profile

Tools using Whisper

Related Models

  • Mega ASR
    Mega-ASR is an open-source robust automatic speech recognition model built for difficult real-world audio with noise, far-field speech, obstruction, echo, distortion, and transmission dropout.
    🗒Transcription🔊Audio enhancement🎙️Voice detection
    NewMultimodal
    Released 1mo ago
  • Bonsai 27B mlx 1bit
    1-bit quantized version of the 27B-parameter Qwen3.6-27B language model, using binary g128 weight representation (1.125 bits per weight) for a ~3.9GB deployed footprint, about 14.2x smaller than FP16. Supports a 262K token context, retains around 89.5% of FP16 accuracy across reasoning, math, coding, and tool-use benchmarks, and runs on-device on phones, laptops, and GPUs via Apple MLX and CUDA.
    💬Chatting💻Coding🔢Math
    NewMultimodal
    Released 14d ago
  • Hy3 preview
    Hy3 Preview is Tencent’s new open-source flagship AI model, built for real-world business use and stronger agentic performance. SCMP reports it has 295B parameters, is Tencent’s most powerful model so far, and is already being deployed in products including Yuanbao and CodeBuddy.
    💬Chatting💻Coding🤖Agents🎩Sophisticated reasoning
    NewMultimodal
    Released 2mo ago
Last updated: April 6, 2026
0 AIs selected
Clear selection
#
Name
Task