text-to-speech
Installation
SKILL.md
Deepgram Text-to-Speech
Deepgram serves two text-to-speech families on separate endpoints, and the voices do not overlap.
Aura voices run only on /v1/speak. Flux TTS voices run only on /v2/speak. /v2/speak is an
additional endpoint. /v1/speak is unchanged and remains supported.
Pick the family first
| Need | Family | Endpoint |
|---|---|---|
| A voice agent that streams LLM output and must survive barge-in | Flux TTS | wss://api.deepgram.com/v2/speak |
| One-shot audio: a file, an IVR prompt, a notification | Flux TTS batch | POST https://api.deepgram.com/v2/speak |
| One response that switches between English and Spanish | Aura-2 codeswitching voice | /v1/speak |
| A non-English voice inside a Voice Agent | Aura-2 | agent.speak.provider.version: "v1" |
An existing aura-2-* or aura-{voice}-en voice you must keep |
Aura-2 or Aura-1 | /v1/speak |