Audio Management

TTS voice profiles, training samples, and pre-generated VoiceBot responses

Voice Profiles
Training Samples
Cached Responses
Emma (Default)
Female · English · Pre-trained · Natural
Neural · English · Female · 22kHz
eleven_multilingual_v2
1,247 generations · Last used 2h ago
0:03
Active in 3 projects
James (Male)
Male · English · Pre-trained · Professional
Neural · English · Male · 22kHz
eleven_english_v1
312 generations · Last used 1d ago
0:03
1 project
Clone Custom Voice
🎤
Upload 1–5 min reference audio
.wav, .mp3 accepted
ElevenLabs Instant Voice Cloning. Higher quality with longer reference audio.
Generate Audio (TTS)
Generate speech audio from text using AI voices. Select a voice, type your text, and adjust quality settings.
Voice Quality Settings▶
Higher = more consistent voice. Lower = more expressive variation.
Higher = closer to original voice. Lower = more natural variation.
Controls expressiveness. 0 = neutral delivery.
Increases similarity to original voice. May increase latency.
Estimated: ~1,200 characters · $0.018
0:00
Naturalness: 4.2/5 · Similarity: 0.89 · Duration: 3.2s