Scribe
ElevenLabs has introduced Scribe, an advanced Automatic Speech Recognition (ASR) model designed to deliver highly accurate transcriptions across 99 languages. Scribe is engineered to handle diverse real-world audio scenarios, providing features such as word-level timestamps, speaker diarization, and audio-event tagging. Benchmark tests, including FLEURS and Common Voice, demonstrate Scribe's superior performance over leading models like Gemini 2.0 Flash, Whisper Large V3, and Deepgram Nova-3, achieving the lowest word error rates in languages such as Italian (98.7%) and English (96.7%). Notably, Scribe also significantly reduces errors in languages that have been traditionally underserved, including Serbian, Cantonese, and Malayalam, where other models often exhibit error rates exceeding 40%. Developers can integrate Scribe through ElevenLabs' speech-to-text API, receiving structured JSON transcripts that include detailed annotations.
Learn more
Le Scribe Audio
Le Scribe Audio is a web-based audio and video transcription service for works councils, local authorities, researchers, legal professionals, and transcription providers. Users upload recordings to generate time-coded transcripts with speaker identification, then review the text alongside synchronized playback and edit speaker labels. The service also provides AI-generated summaries and exports in Word, PDF, TXT, and SRT formats. Its workflow is designed for meeting minutes, interviews, hearings, and other recorded discussions where users need searchable text and structured notes. Optional human proofreading is available as a separate service. Le Scribe Audio is accessed through a browser and provides a workspace for managing recordings and transcripts.
Learn more
QuickWhisper
QuickWhisper is a macOS application for transcription, dictation, and AI summarization using OpenAI's Whisper model. It runs entirely on-device with no cloud dependency required.
The application transcribes audio from local files, YouTube videos, online meetings, and system audio. QuickWhisper can record meetings with calendar integration while keeping the recording interface hidden during screen sharing.
System-wide dictation works across all macOS applications, replacing keyboard input with voice. All transcription runs on your Mac.
AI summarization is available through cloud providers (OpenAI, Anthropic, Google, xAI, Mistral, Groq) or on-device via Ollama and LM Studio.
QuickWhisper also includes batch transcription, Watch Folders for automatic background transcription, speaker diarization, Apple Shortcuts integration, and webhooks for third-party service integration.
Learn more
FastScribe
AI transcription tool that converts audio and video to text with timestamps and automatic speaker labels. Identifies who is speaking and separates the transcript into labelled turns, which you can rename.
Supports MP3, M4A, WAV, AAC, FLAC, OGG, Opus, WMA, AMR, MP4, MOV, WEBM, AVI, MKV and more. Exports TXT, SRT, VTT and DOCX subtitles with speaker names included.
Free tier with no signup required for the first file, speaker labels included.
Speech recognition and speaker diarization both run on private self-hosted GPU hardware, and audio is deleted immediately after transcription.
Supports Spanish, French, German, Portuguese, Italian, Japanese, Hindi, Korean and more.
Learn more
