Transcribe Customer Support Calls
Convert customer support call recordings to searchable text for quality assurance, training, and compliance.
Audio Transcriber
Speech-to-text with speaker labels
Convert spoken audio into accurate text with AI speech recognition. Supports 99+ languages, speaker diarization, word-level timestamps, and audio event tagging. Perfect for meetings, interviews, podcasts, and lectures.
Transcribe Audio
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 99+ languages.
Returns: Full transcription text, word-level timing data with speaker labels, detected language, and confidence scores
Parameters
audio_url *stringPublicly accessible URL of the audio file to transcribe (MP3, WAV, M4A, FLAC, OGG, etc.)
language_codestringISO 639-1 language code (e.g. "en", "es", "fr"). If omitted, language is auto-detected.
diarizebooleanEnable speaker diarization to identify and label different speakers in the audio.
num_speakersintegerExpected number of speakers (1-32). Helps improve diarization accuracy when known.
timestamps_granularitystringGranularity of timestamps in the response. "word" returns per-word timing, "character" returns per-character timing.
tag_audio_eventsbooleanTag non-speech audio events such as laughter, applause, music, and background noise.
Example
Basic transcription of an audio file
curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
-d '{
"tool": "audio-transcriber",
"skill": "transcribe_audio",
"input": {
"audio_url": "https://example.com/podcast-episode.mp3"
}
}' \
https://api.toolrouter.com/v1/tools/callQuick Start
MCP (Claude Code)
claude mcp add --transport stdio \
--env TOOLROUTER_API_KEY=YOUR_API_KEY \
toolrouter -- npx -y toolrouter-mcpREST API
curl -H "Authorization: Bearer $TOOLROUTER_API_KEY" \
-d '{"tool":"audio-transcriber","skill":"transcribe_audio","input":{}}' \
https://api.toolrouter.com/v1/tools/callUse Cases
Convert Voice Memos to Text
Turn voice memos and dictated notes into written text for easy searching, sharing, and organizing.
Dub Marketing Videos
Translate and dub your marketing videos into multiple languages to reach international audiences.
Remove Background Noise from Recordings
Clean up recordings by removing background noise, hum, wind, and environmental sounds.
Workflows
Audio Content Repurposing
Transform audio content into multilingual text and audio formats, informed by social media trends.
Interview Post-Production
Streamline interview editing with speaker isolation, transcription, video editing, and custom graphics.
Frequently Asked Questions
How many languages does it support?
It supports 99+ languages and can auto-detect the language from the audio.
Can I get speaker labels and timestamps?
Yes. Turn on diarization for speakers, and choose word-level timestamps when you need subtitle-style timing.
Can it tag non-speech audio like laughter or applause?
Yes. Enable audio event tagging to capture sounds like laughter, applause, and music.
Should I clean noisy audio first?
If the recording is messy, run it through `audio-isolator` first for better transcription quality.