text-to-speech

Generate natural speech from text - supports 70+ languages, multiple models for quality vs latency tradeoffs. Setup: See Installation Guide . For JavaScript, use @elevenlabs/* packages only. Use pre-made voices or create custom voices in the dashboard. Popular voices: Fine-tune how the voice sounds: Force specific language for pronunciation: Controls how numbers, dates, and abbreviations are converted to spoken words. For example, "01/15/2026" becomes "January fifteenth, twenty twenty-six": When generating long audio in multiple requests, the audio can have pops, unnatural pauses, or tone shifts at the boundaries. Request stitching solves this by letting each request know what comes before/after it: For real-time applications, use the stream method (returns audio chunks as they're generated): See references/streaming.md for WebSocket streaming. Common errors: Monitor character usage via response headers ( x-character-count , request-id ): - JBFqnCBsd6RMkjVDRZzb - George (male, narrative) - EXAVITQu4vr4xnSDxMaL - Sarah (female, soft) - onwK4e9ZLuTAKqWW03F9 - Daniel (male, authoritative) - XB0fDUnXU5powFXDhCwa - Charlotte (female, conversational) - Stability : How consistent the voice stays.