ElevenLabs Text-to-Speech

Generate natural-sounding speech from text using ElevenLabs' neural TTS models.

POST
/api/v1/models/elevenlabs/tts

Convert text to speech with customizable voices

Model
ElevenLabs Multilingual v2
Cost
10 credits/1000 chars
Output
MP3 / PCM Audio

Request Body

NameTypeDescription
textrequiredstringText to convert to speech (max 10,000 characters)
voicestringDefault: adamVoice preset: adam, antoni, josh, rachel, domi, bella
voice_idstringElevenLabs voice ID (overrides voice preset)
model_idstringDefault: eleven_multilingual_v2TTS model to use
stabilitynumberDefault: 0.5Voice stability (0-1). Lower = more expressive
similarity_boostnumberDefault: 0.75Voice similarity (0-1). Higher = closer to original voice
output_formatstringDefault: mp3_44100_128Audio format: mp3_44100_128, mp3_44100_64, pcm_16000, pcm_22050

Available Voices

adam
Deep, authoritative male voice. Great for narration.
rachel
Calm, pleasant female voice. Perfect for ASMR content.
josh
Young, energetic male voice. Great for engaging content.
bella
Soft, young female voice. Approachable and friendly.
Get the full voice list with GET /api/v1/models/elevenlabs/voices

Example Request

"text">-purple-600">curl "text-blue-600">-X POST https://vydra.ai/api/v1/models/elevenlabs/tts \
  "text-blue-600">-H "Authorization: Bearer YOUR_API_KEY" \
  "text-blue-600">-H "Content">-Type: application/json" \
  "text-blue-600">-d '{
    "text": "Welcome to Vydra. The easiest way to create AI videos.",
    "voice": "adam",
    "stability": 0.5,
    "similarity_boost": 0.75
  }'

Response

{
  "audioUrl": "https://cdn.vydra.ai/audio/tts/org_123/1706300000000.mp3",
  "voiceId": "pNInz6obpgDQGcFmaJgB",
  "characterCount": 52,
  "creditsCharged": 1,
  "durationMs": 1234,
  "format": "mp3"
}

Use Cases

🎬 Video Voiceovers
Generate professional narration for your AI videos.
📱 App Notifications
Create audio for in-app voice feedback.
🎧 Podcasts
Automate podcast intro/outro generation.
📚 Audiobooks
Convert written content to audio format.