Full Flux TTS support on dg speak
GAUnverifiedAdded Sep 24, 2026
dg speak now defaults to flux-alexis-en on Speak v2 (WebSocket streaming) instead of Aura 2. Synthesised audio differs from earlier releases unless you request an Aura model explicitly: dg speak "Hello from Deepgram" -m aura-2-asteria-en -o hello.mp3 Two Flux-only controls are now available.
Topics: AI agents, Streaming, Governance, Data integration, Observability
More Deepgram releases
Every Deepgram release| Date | Release | Type |
|---|---|---|
| Aug 19 | Deepgram CLI 0.3.0: Flux TTS and Flux STTunverified GA | GA |
| Aug 19 | Flux STT streaming is fixedunverified Update | Update |
| Aug 19 | Redaction and numerals on dg listenunverified Update | Update |
| Aug 19 | Exit codes are now enforcedunverified Update | Update |
| Aug 19 | Error output moved to stderrunverified Update | Update |
| Aug 19 | dg update now delivers the whole releaseunverified Update | Update |
| Aug 19 | Also in this releaseunverified Update | Update |
| Aug 17 | Nova-3 Adds Afrikaans and Georgian, Plus Improved Models for Hungarian, Macedonian, Russian, Slovak, Slovenian, and Urduunverified Update | Update |
Also shipped on Aug 19, 2026
Deepgram in August 2026
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.