You can add transcription, realtime voice agents and generated audio to an app through one gateway key, with usage and cost tracked beside your LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → traffic. A 50% discount runs through November 9.
Key takeaways · AI-distilled
Vercel AI Gateway now serves 14 ElevenLabs models across speech to text, streamingSending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.Full definition → text to speech, realtime voice agents, music, sound effects, and multi-voice dialogue, all under one gateway API key.
Vercel's example chains Scribe v2 Realtime transcription, a text model of your choice, and Eleven Flash v2.5 speech, so each stage can be swapped without changing the rest of the pipeline.
Eleven Realtime v1 Max and Mini handle the whole spoken exchange over one WebSocket; the server only mints a short-lived tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →, and the models support semantic voice activity detection but not server-vad.
Vercel says the Gateway passes through provider pricing with no markup or platform fee, and ElevenLabs models are 50% off on it through November 9.
Terms in this piece · Glossary
streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
