Codex Voice
ChatGPT transcription and voice, through your own server.
An unofficial Rust server that uses your existing Codex ChatGPT subscription login for audio transcription and voice conversations. It reproduces the reverse-engineered flow the ChatGPT app uses, through private ChatGPT services.
- The server is the product; its browser demo is an optional way to test your server and account
- Your audio still goes to private ChatGPT services, not OpenAI's public Realtime API; routes can change
- Source on GitHub; no tags, binaries or images released yet
- HTTP through the local gateway
- WebRTC media, not via the gateway
- your machine; arrows leaving it carry audio
- A · Transcriptions
- B · Realtime
Transcriptionsone audio file in, its text out
Send a recorded file as a multipart form. The gateway passes it upstream with your Codex login and returns the text in the format you asked for.
POST /v1/audio/transcriptions
current route · multipart| field | what happens |
|---|---|
| filerequired | The audio to transcribe. It can't be empty. |
| language | A hint, forwarded upstream. Without it the server's --language applies. |
| response_ | json (default) text verbose_json. Not supported: srt, vtt. |
| model | Accepted so existing clients don't break, then ignored. It doesn't pick the backend. |
The 10 MiB default limit covers the whole multipart body, not just the file.
# local server key, not your Codex token
curl --fail-with-body http://127.0.0.1:2600/v1/audio/transcriptions \
-H "Authorization: Bearer $CODEX_VOICE_API_KEY" \
-F 'file=@recording.wav;type=audio/wav' \
-F language=en -F response_format=json127.0.0.1:2600 is the default address. Leave out the header only on a server started with --no-api-key.
{"text":"Recognized speech."}The README's example wording, not a recorded output.
Realtimea live voice session your client owns
The gateway only does the handshake. Your client sends a WebRTC offer, gets an answer back, and from then on talks to upstream directly: microphone, playback and the data channel are all yours.
- clientCreates a WebRTC offer with its microphone track.
- client → gatewayPOSTs the offer as JSON with the local key. No Codex token is ever handed to the browser.
- gateway ↔ upstreamNegotiates with upstream using your local Codex login. Upstream picks the voice backend.
- gateway → clientReturns the SDP answer and a session_id for correlation.
- client ↔ upstreamAudio and events flow over WebRTC. They never come back as REST JSON, and the gateway does not relay media.
- clientStop means the client closes the connection and releases the mic. There are no pause, resume or delete endpoints.
POST /v1/realtime/sessions
private JSON · subject to changeThe old /v1/voice/* routes are gone; this is the only signalling route.
{
"sdp": "<your peer's complete SDP>",
"mode": "standard",
"voice": "cove",
"history_and_training_disabled": true
}sdp is a placeholder; a real offer comes from your client's peer connection. Unknown fields are rejected.
- sdp
- The SDP answer. Apply it to the peer that made the offer.
- session_id
- A correlation id for logs. It isn't a handle for controlling the session.
| field | values · default |
|---|---|
| sdprequired | Your complete WebRTC audio offer, up to 128 KiB. |
| mode | standard advanced wingman. default advanced. The demo starts on Wingman with saving off, and asks you to turn saving on before a Wingman or Advanced Start. A mode picks private service behaviour, not a verified model. |
| voice | default cove |
| language | Optional, such as en-US. Left out, the language is detected. |
| enable_ | default true: user and assistant text events. |
| history_ | default true. false lets ChatGPT save the conversation. The JSON route forwards either value for every mode; only the demo requires saving for Advanced and Wingman. |
| timezone, timezone_ | default UTC, 0 |
Where things liveoperational boundaries
your client
- owns the WebRTC connection, mic, playback and data channel
- handles Stop and cleanup
codex-voice gateway
- transcription requests and realtime signalling
- never relays realtime media
- 127.0.0.1:2600, one upstream request at a time by default
upstream
- private ChatGPT service, reached with your Codex login
- chooses the voice backend
- its retention terms are its own; this project makes no promise about them
Not claimed on this page
- official OpenAI product
- OpenAI's Realtime API or GPT-Live
- stable public API
- a live Hermes or Discord voice bridge
- a packaged release
- free or unlimited
- fully local or offline
- measured speed or quality
- zero retention
Limitsthe not-unlimited part
Codex Voice doesn't add minutes. Your ChatGPT plan has published Voice allowances, and the gateway doesn't get around your account's limits.
| plan | Live usage, rolling 24 hours |
|---|---|
| Go | 3 hours with GPT-Live-1.1 Quip |
| Plus | 3 hours with GPT-Live-1.1 |
| Pro ($100/month) | 15 hours with GPT-Live-1.1 |
| Pro ($200/month) | Unlimited GPT-Live-1.1, subject to abuse guardrails |
15 hours talking. Eight hours sleeping. One hour left for bathroom breaks. Surprisingly considerate.Pro ($100) arithmetic on a nominal day, not a reset time or a promise.
- These are OpenAI's published allowances for Voice in ChatGPT, not measured Codex Voice quotas. The private service behind the gateway may count, limit or reject sessions in its own way.
- The window rolls over 24 hours. Nothing resets at midnight, and ChatGPT tells you when you reach a limit.
- One Voice conversation at a time. A conversation can end at a usage limit, at the maximum session length, or when a long one reaches its context limit.
- They don't cover file transcription (lane A) and they aren't OpenAI's public Realtime API pricing.
- Codex Voice has no usage meter or countdown. When upstream says no, you get an error (often 429).
- Workspace plans: Business Standard and Business Premium get 3 and 15 hours, then 1.25 credits per minute. Voice in the desktop app has separate pricing and limits.
Development status
Open source on GitHub main 1af74b1
The server, CLI, Rust library and optional browser demo, MIT and derived from codex-asr. Build it from source.
File STT in production 4 Hermes gateways
Dima's four Hermes gateways now send voice-note transcription to Codex Voice. Each passed a real public Ogg/Opus sample with LLM post-processing, with no fallback or errors.
Demo accepted by its owner
The project's owner accepted the working browser demo.
Wider voice acceptance next
Every mode in every browser, and a live Hermes or Discord voice bridge, are not done. File STT is a different, narrower path.
Release not yet
No tags, binaries or images yet. Upstream codex-asr releases are not Codex Voice builds.
Public, early.
File transcription runs in production for its author, and the demo works. Wider voice acceptance and packaged releases are still to come. This page shows how the project works; it isn't test evidence.
Source github.com/dmmeteo/codex-voice
Docs README HTTP API configuration voice guide
Codex Voice is an unofficial, independent project. It is not affiliated with or endorsed by OpenAI, and it doesn't add plan access or lift usage limits. Its code is MIT, derived from codex-asr, with the inherited copyright notice kept in its licence.
Facts on this page come from the project's README and its API, configuration and voice docs at 1af74b1. Request blocks follow them; placeholders are marked. Type on this page: Excalifont (Excalidraw) and Geist Mono (Vercel), both SIL OFL-1.1.