Introducing Audio Intelligence: Transcription + Speaker Labels for $0.002/min

LeanVox started as a text-to-speech API. Today it handles both sides of audio.

Meet Audio Intelligence — transcription, speaker diarization, and AI summarization in a single API call. Same API key. Same dashboard. No new account.

One endpoint. Three outputs.

from leanvox import Leanvox

client = Leanvox(api_key="lv_live_...")

result = client.audio.transcribe(
    file="meeting.mp3",
    features=["transcribe", "diarize", "summarize"]
)

print(result.formatted_transcript)
# SPEAKER_0: Welcome to the show.
# SPEAKER_1: Thanks for having me.

print(result.summary)
# "Team discussed Q1 roadmap priorities..."

Or with Node.js:

const result = await client.audio.transcribe({
  file: "meeting.mp3",
  features: ["transcribe", "diarize", "summarize"]
})

console.log(result.formatted_transcript)
console.log(result.summary)

Pricing that actually makes sense

We benchmarked Whisper Large V3 + Pyannote 3.1 on dedicated GPU hardware. The COGS came out to $0.0006 per 5 minutes. We're passing those savings to you:

4.75× cheaper than AssemblyAI. 9× cheaper than Deepgram. Speaker labels included free.

Your $1.00 signup credit covers 500 minutes of transcription. A 1-hour meeting costs $0.12.

Why diarization is free

Most providers charge extra for speaker detection. We don't, because our infrastructure makes it nearly zero marginal cost — it adds less than 0.5 seconds to processing.

We'd rather bundle it and give you a better product than charge for a feature that costs us almost nothing to provide.

Works with the MCP server too

If you're using Claude or another MCP-compatible AI, no code required:

{
  "mcpServers": {
    "leanvox": {
      "command": "npx",
      "args": ["leanvox-mcp"],
      "env": { "LEANVOX_API_KEY": "lv_live_..." }
    }
  }
}

Then just tell Claude: "Transcribe this audio file and give me a summary with speaker labels." It calls the API and returns the result — no code, no SDK, no setup.

What's supported

• Formats: mp3, wav, ogg, flac, m4a, webm (up to 500MB)
• 99 languages (auto-detected or specify)
• Files under 5 minutes return synchronously. Longer files use async processing with webhook callbacks.
• SDK support: Python and Node.js (v0.3.0)

Getting started

# Install
pip install leanvox  # or npm install leanvox

# Transcribe in 3 lines
curl -X POST https://api.leanvox.com/v1/audio/transcribe \
  -H "Authorization: Bearer lv_your_key_here" \
  -F "[email protected]"

→ Quickstart guide · API reference · Get your API key