Voice Over & ElevenLabs

Record your voice. Select a model from ElevenLabs. Hit Generate and import to timeline.

That’s it.

No roundtripping. No file management. No leaving Premiere.

Pick Any ElevenLabs Voice

Every ElevenLabs model on fal.ai is available inside modelBridge — and new ones show up automatically as they launch.

Text to Speech

Model	What it does
elevenlabs/tts/eleven-v3	Their best model — with emotion tags for expressive delivery
elevenlabs/tts/turbo-v2.5	Ultra-fast generation for quick iterations
elevenlabs/tts/multilingual-v2	29 languages, one model
elevenlabs/text-to-dialogue/eleven-v3	Multiple speakers in a single generation

Voice Conversion

Model	What it does
elevenlabs/voice-changer	Record in your voice, output in any other

Sound Effects & Music

Model	What it does
elevenlabs/sound-effects/v2	Describe a sound, get the audio
elevenlabs/music	Generate music from a text prompt

Transcription

Model	What it does
elevenlabs/speech-to-text/scribe-v2	High-accuracy speech to text
elevenlabs/speech-to-text	Standard transcription

Dubbing

Model	What it does
elevenlabs/dubbing	Dub your video into another language

Control the Performance

The eleven-v3 models support emotion tags. modelBridge puts them in a clickable tag bar right above your script:

[laughing] [whispered] [excited] [sighs] [crying] [shouting]

Click a tag, it inserts at your cursor. Want something custom? Just type [cheerful] or [slowly] directly — the model understands freeform tags too.

For Agencies

Record a rough VO for timing. Transform it to a professional voice in seconds. Don’t like it? Pick a different voice, tweak the emotion, regenerate. Want to hear two options? Dual Mode runs both side by side from the same script.

No casting calls. No studio time. No audio engineer. Just you, Premiere, and a voice that sounds exactly how the edit needs it to sound.