Providers · Vendor API
ElevenLabs
ElevenLabs speech, music, sound effects and transcription through your own ElevenLabs API key and the official SDK, with models such as Eleven v3 for text-to-speech from the premade voice library and Scribe for transcripts with speaker labels. Requests go straight from your machine to ElevenLabs and usage draws on your own plan's credits.
Audio(5 models)
v3
ElevenLabs' most expressive voice model with rich emotional and tonal range.
Text-to-speech · 6 months ago (Mar 2026)
Scribe v2
ElevenLabs' batch transcription model, which returns word-level timing for subtitles and can label who is speaking.
Speech-to-text · 8 months ago (Jan 2026)
Sound Effects v2
ElevenLabs' text-to-sound-effects model: foley, ambiences and impacts up to 30 seconds, with seamless looping for background beds.
Sound effects · 1 year ago (Sep 2025)
Music
ElevenLabs music generation model for creating original AI-composed tracks.
Music · 1 year ago (Aug 2025)
Flash v2.5
ElevenLabs' fastest speech model, with about 75 ms latency across 32 languages at half the per-character price of Multilingual v2.
Text-to-speech · 1 year ago (Dec 2024)