Token Plan

Access all Lens Audio API features with a simple token-based subscription. Purchase tokens and use them across every endpoint — TTS, streaming, voice cloning, and more.

Included Features

Text-to-Speech API access
Streaming TTS via Server-Sent Events
Voice cloning with custom audio
8 emotion styles
Speed control (0.5x - 2.0x)
Custom emotion vectors
Queue priority access
Usage analytics dashboard

Audio API

Active

Full access to TTS, streaming, voice cloning, and all API endpoints. Token-based usage metering with real-time tracking.

3,000 BPE tokens per request limit. Queue-based rate limiting with priority access for subscribers.

Manage Your Plan

Quick Start

1. Get your API key

Navigate to the page and create a new secret key. Keep it secure — it won't be shown again.

2. Make your first request

Use the TTS endpoint to generate speech from text:

bash

curl -X POST https://audio-chat.ask-lens.ai/audio/tts \
  -H "Authorization: Bearer ak_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, welcome to Lens Audio!", "voice_id": "zh-Somer"}' \
  --output output.wav

3. Explore the API

Check the full for all available endpoints including streaming TTS, voice cloning, and usage tracking.

FAQs

Full access to all TTS endpoints, streaming, voice cloning, and usage analytics. Every API feature is available from day one.

Each request supports up to 3,000 BPE tokens. This is sufficient for most paragraphs and short articles.

The API uses queue-based rate limiting. You can check current queue utilization via GET /audio/queue-status before submitting requests.

Currently the API outputs WAV format audio. MP3 and FLAC support is planned for the Pro Plan.

Yes. Audio generated through the API is yours to use commercially with no additional licensing required.

Use your API key via the Authorization header (Bearer token) or the X-API-Key header. Create keys from the User Center.