Text to Speech
Loading…
Generate Speech
Variable Stable
Low High

Your Voices

🎙
No voices yet. Clone a voice to get started.
Clone from File

Upload a clean WAV or MP3 (5–15 seconds). Trim long files with ffmpeg first: ffmpeg -i input.wav -t 12 -ar 24000 -ac 1 ref.wav

🎵
Drop audio files here or browse
WAV, MP3 · Max 50MB each
Speech to Speech

Upload source audio. It will be transcribed via Whisper and re-synthesised using the target voice.

🎤
Drop source audio or browse
My Profile
Loading…
Usage This Month
Preferences
API Keys

Use API keys to connect your PBX and chatbot without browser login.
Header: xi-api-key: vg_xxxx…

Total Users
Active
Chars This Month
User Management
USER ROLE STATUS CHARS/MONTH LIMIT VOICES MAX VOICES ACTIONS
Loading…
API Settings
API Reference

This server is ElevenLabs API v1 compatible. You can use any ElevenLabs SDK or client by pointing it to this server URL.

Key endpoints:
POST /v1/text-to-speech/{voice_id}
POST /v1/text-to-speech/{voice_id}/stream
WS /v1/text-to-speech/{voice_id}/ws
POST /v1/voices/add
GET /v1/voices
POST /v1/speech-to-speech/{voice_id}

Full docs: /docs (Swagger UI)