NEWVectors or files. Pick a path.Start →
    Models/Speech & Audio/CohereLabs/cohere-transcribe-03-2026
    HFTranscriptionapache-2.0

    cohere-transcribe-03-2026

    by CohereLabs

    #1 on Open ASR Leaderboard with 14-language support

    817Kdl/month
    1,038likes
    2.1Bparams
    Identifiers
    Model ID
    CohereLabs/cohere-transcribe-03-2026
    Feature URI
    mixpeek://transcription@v1/cohere_transcribe_03_v1

    Overview

    Cohere Transcribe is a 2B-parameter automatic speech recognition model that ranks #1 on the Open ASR Leaderboard for English. Trained on 500K hours of audio data, it delivers 3x faster real-time processing compared to models of similar accuracy. The model supports 14 languages with strong multilingual performance.

    For multimodal search pipelines, accurate transcription is foundational -- every word in the transcript becomes searchable text. Higher transcription accuracy directly translates to better full-text search over audio and video content.

    Architecture

    Encoder-decoder architecture optimized for streaming and batch ASR. 2B parameters trained on 500K hours of diverse audio. Supports NeMo framework for enterprise deployment.

    Mixpeek SDK Integration

    import { Mixpeek } from "mixpeek";
    
    const mx = new Mixpeek({ apiKey: "API_KEY" });
    
    // Managed: create a collection over a bucket; Mixpeek runs this model's extractor
    const collection = await mx.collections.create({
      namespace_id: "my-namespace",
      collection_name: "my-collection",
      source: { type: "bucket", bucket_ids: ["bkt_your_bucket"] },
      feature_extractor: {
        feature_extractor_name: "transcription",
        version: "v1",
        parameters: { model_id: "CohereLabs/cohere-transcribe-03-2026" },
      },
    });

    Capabilities

    • #1 on Open ASR Leaderboard (English)
    • 14 language support with strong multilingual accuracy
    • 3x faster than comparable accuracy models
    • Apache-2.0 license for commercial use
    • NeMo framework support for enterprise deployment

    Use Cases on Mixpeek

    Video transcription: convert spoken content to searchable text
    Podcast indexing: make every spoken word findable
    Meeting recording search: extract action items and topics from meeting audio
    Multilingual content: transcribe content across 14 languages for unified search

    Specification

    FrameworkHF
    OrganizationCohereLabs
    FeatureTranscription
    Outputtext + timestamps
    Modalitiesvideo, audio
    RetrieverTranscript Search
    Parameters2.1B
    Licenseapache-2.0
    Downloads/mo817K
    Likes1,038

    Research Paper

    Cohere Transcribe

    arxiv.org

    Build a pipeline with cohere-transcribe-03-2026

    Add this model to a processing pipeline alongside other extractors. Combine with retrieval stages for end-to-end search.

    Run on your data, free