From the source
Vercel and
ElevenLabs are partnering to bring 14 ElevenLabs models to AI Gateway, covering speech to text, streaming text to speech, realtime voice agents, music, sound effects and multi-voice dialogue.
- All of them are reachable through a single gateway API key, so an app can transcribe a user, reason over the text with any of hundreds of models, and answer in an ElevenLabs voice.
- To celebrate the launch, Vercel says all ElevenLabs models are 50% off on AI Gateway for the first 14 days, through November 9th.
- Every request lands in the same usage, cost and trace views as other AI Gateway traffic.
- Because each step is its own model, developers can swap the transcription, language or speech model without touching the rest of the pipeline.
- The realtime models run a whole spoken conversation in one model over a single WebSocket session, and support semantic voice activity detection but not server-vad.
