OpenAI adds realtime translation model

// 1h agoMODEL RELEASE

OpenAI adds realtime translation model

OpenAI introduced GPT-Realtime-Translate in the Realtime API, a live speech translation model that supports 70+ input languages and 13 output languages. It ships alongside new realtime voice and transcription models for developers building low-latency voice apps.

// ANALYSIS

OpenAI is turning translation into an API primitive instead of a separate pipeline step, which is the right move if it wants voice apps to feel native rather than stitched together.

–Live translation inside the same realtime stack reduces the need to chain ASR, MT, and TTS services
–The 70+ to 13 language matrix makes this immediately useful for support, events, education, and cross-border sales
–Pricing per minute suggests OpenAI wants production adoption, not just a demo loop
–The real test is latency plus accent robustness in messy real-world audio, not benchmark fluency
–Bundling translation with GPT-Realtime-2 and GPT-Realtime-Whisper signals a broader voice platform, not a one-off feature

// TAGS

gpt-realtime-translatespeechsttapimultimodalinference

DISCOVERED

1h ago

2026-05-07

PUBLISHED

2h ago

2026-05-07

RELEVANCE

9/ 10

AUTHOR

OpenAI

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS29m ago

ElevenHacks, Cursor push voice-only challenge

ElevenLabs’ eighth weekly hackathon asks builders to use Cursor and ElevenLabs voice APIs to create something fully operable without a keyboard. The contest is live now, with cash prizes, social-post scoring, and a free month of ElevenLabs Creator for participants.

UPDATE1h ago

Entire CLI adds recap, review, labs

Entire shipped three new CLI commands aimed at making agent-driven development easier to inspect and control. `entire recap` summarizes recent agent activity across repos and time windows, `entire review` runs configured review skills against the current branch with checkpoint context, and `entire labs` surfaces experimental workflows while the interface is still evolving. The update pushes Entire further toward a workflow layer for tracking, reviewing, and replaying AI coding sessions instead of treating agent output as a one-off diff.

OPEN SOURCE1h ago

OpenCode plugin fades radio as agents work

opencode-vibe-mode is an OpenCode TUI plugin that adds background music while you work, keeping audio at a lower cruise volume and automatically fading it up when an agent is active. It includes built-in stations like house, lofi, and jazz, plus commands to toggle the vibe, restart playback, and cycle stations. Setup is lightweight but opinionated: it depends on `mpv` and `yt-dlp`, and can be installed directly from GitHub or wired in locally or globally.