Lector API

Lector It

Lector can turn text, URLs, documents, and images into audio with a clean API built for developers, agents, and automation.

What Lector can turn into audio

  • Text and content - direct audio generation
  • URLs - public pages into audio
  • Documents and document URLs - readable content into audio
  • Images and image URLs - readable content into audio
  • Files and links - flexible workflows for apps and agents

Choose the voice that fits the job

Select the ideal voice provider and voice style for narration, briefings, instructions, accessibility, agents, robotics interfaces, newsletters, marketing content, and publisher and media audio workflows.

OpenAI voices

Use polished, natural voices for general-purpose narration, articles, documents, and app experiences.

Examples: alloy, nova, coral, onyx, cedar, marin

xAI voices

Choose crisp expressive voices with distinct personalities for energetic, warm, professional, balanced, or authoritative delivery.

Examples: eve, ara, rex, sal, leo

Gemini voices

Access a broad voice palette for different tones, styles, and multilingual audio experiences.

Examples: Zephyr, Puck, Kore, Aoede, Charon

Pass tts_provider and voice in your request, then choose stream or signed URL delivery. Provider access follows your API plan.

{
  "url": "https://example.com/article",
  "tts_provider": "openai",
  "voice": "nova",
  "delivery": "url"
}

Generate narrated audio for articles, online publications, newsletters, documents, instructions, image-based text, robots, apps, and agents.

Choose how audio is delivered

  • stream - direct audio response
  • url - signed audio file URL
  • async_url - background job for supported endpoints
  • auto - Lector chooses the delivery path

Auto is convenience. Explicit settings are control. Use auto when you want Lector to choose the best delivery path, or use url, stream, or async_url when you need exact behavior. URL responses include an audio URL; async jobs return a job and status flow. callback_url is available for async-capable API workflows.

Built for agents and automation

  • OpenAI tool use workflows
  • Claude-style reasoning workflows
  • Local and autonomous agents
  • Slack, Telegram, and automation workflows
  • Accessibility and assistive workflows

Quick examples

curl -X POST https://api.lectorai.app/v1/tts \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "text": "Hello from Lector",
      "voice": "marin",
      "delivery": "url"
    }'
curl -X POST https://api.lectorai.app/v1/listen-url \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "url": "https://example.com/article",
      "delivery": "url"
    }'

Core endpoints

  • /v1/tts
  • /v1/listen-content
  • /v1/listen-url
  • /v1/listen-document
  • /v1/listen-document-url
  • /v1/listen-image
  • /v1/listen-image-url
  • /v1/capabilities

Simple billing flow

Start with API access, generate audio, and scale usage as your application grows.

Start building with Lector API