Audio Transcriber
Speech-to-text with speaker labels
On it. Running Audio Transcriber now and I'll bring the results straight back here.
Try asking
About
Audio Transcriber converts spoken audio into accurate text with speaker labels, word-level timestamps, and audio event tagging. It supports 90+ languages with automatic detection, making it suitable for meetings, interviews, podcasts, lectures, and any multi-speaker recordings.
Getting clean, structured transcripts normally requires a separate service and manual cleanup. This tool handles language detection, speaker diarization, timestamp granularity, and non-speech event tagging (laughter, applause, music) in a single call. The output includes both a full transcript string and a per-word array with timing and speaker IDs — ready for subtitles, summaries, or further analysis.
What you can do
- Transcribe any audio file from a URL in 90+ languages with automatic language detection
- Label different speakers separately (diarization) with or without knowing the speaker count
- Get word-level or character-level timestamps for subtitle generation
- Tag non-speech audio events like laughter, applause, and background music
- Process MP3, WAV, M4A, FLAC, OGG, and other common formats
- Turn a meeting recording into speaker-attributed notes, decisions, action items, risks, and optional PII-redacted audio
Who it's for
Podcast producers generating episode transcripts. Journalists and researchers transcribing interviews. Teams needing meeting notes with speaker attribution. Developers building transcription pipelines or subtitle generation workflows.
How to use it
- Call transcribe_audio with the URL of your audio file — language auto-detects if you don't specify
- Set diarize: true to get separate speaker labels; add num_speakers if you know the count for better accuracy
- Set timestamps_granularity: "word" if you need per-word timing for subtitle generation
- Enable tag_audio_events: true to capture laughter, applause, music, and other non-speech sounds
Getting started
For noisy recordings, run the audio through Audio Isolator first for cleaner transcription results. Then call transcribe_audio with the cleaned file URL.
Turn a meeting recording into a speaker-attributed transcript and…
Transcribe an audio file from a URL to text using AI speech-to-text
Turn a meeting recording into a speaker-attributed transcript and concise notes covering supported decisions, action items, risks, and open questions, with optional PII redaction.
Transcribe an audio file from a URL to text using AI speech-to-text. Supports speaker diarization, word-level and character-level timestamps, audio event tagging, and automatic language detection for 90+ languages.
List available models for this tool, sorted by popularity. Returns provider details and pricing.
- Meeting notes now use Gemini 3.8 Flash.
- Added meeting intelligence with speaker attribution, evidence-conscious notes, regional routing, and optional PII-redacted audio
- Aligned language coverage with current Scribe v2 documentation.
- Added subtitle, expanded description, and agent instructions
- Initial release
Powered by
Related
Example workflows
Transcribe an interview with speaker labels
Turn a hosted audio recording into searchable text with optional speaker and word timing data.
- Pass the ToolRouter file ID or hosted audio URL to `transcribe_audio`.
- Enable diarization and word-level timestamps when you need speaker attribution or subtitle timing.
- Review the transcript, detected language, speaker labels, and timing data before using it downstream.
Guides
Questions
Can I transcribe an audio file to text?
Yes. Pass a ToolRouter file ID or hosted HTTP(S) URL to `transcribe_audio` to get the full transcript in one call.
Can it separate speakers and add timestamps?
Yes. Enable speaker diarization for labels, and request word-level timestamps when you need subtitle-style timing.
Which languages and audio formats work?
It supports 90+ languages with automatic detection and common formats including MP3, WAV, M4A, FLAC, and OGG.
Can it tag non-speech audio or handle a noisy recording?
Enable audio event tagging for laughter, applause, and music. For messy speech, run `audio-isolator` first.