AssemblyAI LeMUR Voice

by AssemblyAI

AssemblyAI's LLM framework over its ASR for voice intelligence and agents.

Looking at AssemblyAI LeMUR Voice? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min

TL;DR

Best for assemblyAI customers layering LLM reasoning on transcribed audio. Pricing: see vendor pricing.

Category
Transcription APIs
License
—
Stars
—
Last push
—
Pricing
see vendor pricing
Platforms
Cloud, API

What it is

AssemblyAI LeMUR (Large Model Untouched by Rules) is a framework that lets developers query LLMs over AssemblyAI transcripts — summaries, Q&A, action items — with a thin API. For voice-agent use cases it pairs naturally with AssemblyAI streaming ASR and external TTS to power workflows that are voice-in but mostly post-call analysis.

Best for: AssemblyAI customers layering LLM reasoning on transcribed audio.
Watch out for: Built around post-call rather than ultra-low-latency realtime agents.

Features

Speaker diarizationNo
Word-level timestampsNo
Streaming / real-timeNo
Languages supportedNone
HIPAA eligibleNo

AssemblyAI LeMUR Voice vs Whipscribe

FeatureAssemblyAI LeMUR VoiceWhipscribe
CategoryTranscription APIsTranscription APIs
PricingNot verified$4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup
Speaker diarizationNot verifiedYes
Word timestampsNot verifiedYes
StreamingNot verifiedNo
Languages—99
PlatformsCloud, APIWeb, API, MCP

Alternatives to AssemblyAI LeMUR Voice

OpenAI Whisper API
OpenAI

Hosted Whisper large-v3 from OpenAI — $0.006 per minute.

$0.006/min
AssemblyAI
AssemblyAI

Universal-2 model + diarization, PII redaction, topic detection, summarization.

from $0.37/hr
Deepgram
Deepgram

Nova-2 model, excellent streaming, strong at conversational audio.

from $0.0043/min

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.