ElevenLabs Voice Cloning (Instant and Professional)
Two cloning paths: Instant Voice Cloning estimates a voice from 1-2 minutes of audio with no verification, and Professional Voice Cloning fine-tunes a dedicated model from 30-180 minutes of audio.
- Weights
- Not released
- API
- Yes
- Commercial use
- Permitted subject to conditions
PVC requires voice verification and can only be used on your own voice. Clones are then driven by the standard ElevenLabs TTS models.
Instant Voice Cloning has no verification step, but the terms require that you supply either your own recordings or a voice you are authorised to share, and you warrant you hold all necessary rights.
- The free tier is non-commercial. Commercial use of output is permitted on paid plans; free accounts are non-commercial only
- Depends on your plan tier. Commercial use of output is permitted on paid plans; free accounts are non-commercial only
Specification
- What it takes in
- audio, text
- What it makes
- audio
- Controls
- voice-cloning, emotion-control, pronunciation-dictionary
- Weights
- Not released
- API
- Yes
- Pricing
- No separate per-clone fee documented; cloning availability is gated by plan. Instant Voice Cloning is available on all plans including Free. Professional Voice Cloning requires Creator or higher, with 1 slot on Creator/Pro, 3 on Scale, 10 on Business, custom on Enterprise. Generation is billed at the underlying TTS model rate.
- Released or updated
- not established
- Languages
- not established
Strengths
- Instant cloning from 1-2 minutes of audio, available on the free tier
- PVC trains a dedicated model for higher fidelity
- Clear documented consent/verification gate on the high-fidelity path
Weaknesses
- PVC fine-tuning takes 3-6 hours or longer
- PVC needs 30-180 minutes of clean source audio
- PVC slot counts are tight on lower paid tiers
- Instant cloning has no verification, which shifts consent risk entirely onto the user
Best for
- talent voice replication with consent
- self-narration at scale
- pickup lines and ADR
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- The docs' PVC rule ('only your own voice') is stricter than the general terms of use, which contemplate uploading 'the voice you are authorized to share with us'. The stricter product-level rule appears to apply to PVC specifically.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
MCP servers that front ElevenLabs
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
ElevenLabs
ElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription.
-
Elevenlabs
RunAPI MCP server for ElevenLabs: create tasks, poll status, check pricing.
-
Elevenlabs
Convert text to speech, transcribe audio, and dub videos with AI voices.
-
Jellypod
Create, import, and publish Jellypod podcast episodes from your AI assistant.
-
Labs
MCP Server with AI-powered tools including ElevenLabs text-to-speech for realistic voice synthesis.
-
Picsart GenAI
Generate and edit images, videos and audio with 150+ AI models.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
ElevenLabs Agents
A hosted conversational voice stack that chains a fine-tuned speech-to-text model, a selectable LLM, low-latency TTS and a proprietary turn-taking mod
Voice and speech
ElevenLabs Dubbing (v2)
End-to-end dubbing that transcribes, translates and regenerates speech in the source speaker's voice across 90+ languages, with dialect variants in v2
Voice and speech
Eleven v3
ElevenLabs' most expressive text-to-speech model, aimed at emotionally varied narration rather than lowest latency. It supports natural multi-speaker
Voice and speech