[BOT ISSUE] OpenAI: add missing gpt-realtime-translate and gpt-realtime-whisper models

[github-actions]

Gap

Two new OpenAI realtime models are missing from packages/proxy/schema/model_list.json:

1. gpt-realtime-translate — a live translation model that translates speech from 70+ input languages into 13 output languages
2. gpt-realtime-whisper — a streaming speech-to-text model for low-latency realtime transcription

Both were announced on May 7, 2026 alongside gpt-realtime-2. The catalog already includes other realtime models (gpt-realtime-mini, gpt-realtime-1.5) and gpt-realtime-2 is tracked separately in #543.

Verified fields

gpt-realtime-translate

Field	Value	Source
Model ID	gpt-realtime-translate	Model page
Format	openai	Catalog convention for OpenAI models
Flavor	chat	Catalog convention
Max input tokens	16,000	Model page
Max output tokens	2,000	Model page
Available providers	["openai"]	Model page

gpt-realtime-whisper

Field	Value	Source
Model ID	gpt-realtime-whisper	Model page
Format	openai	Catalog convention for OpenAI models
Flavor	chat	Catalog convention
Max input tokens	16,000	Model page
Max output tokens	2,000	Model page
Available providers	["openai"]	Model page

Verification note

• Model existence: Both models confirmed on the OpenAI models listing, their dedicated model pages (translate, whisper), and the launch announcement (three independent official signals).
• Pricing: Both models use per-minute audio pricing ($0.034/min for translate, $0.017/min for whisper) which does not map cleanly to the per-token input_cost_per_mil_tokens/output_cost_per_mil_tokens schema fields. Per-token pricing is not published — pricing fields are omitted rather than guessed.
• Token limits: 16,000 context / 2,000 max output confirmed on each model's detail page.
• displayName: Not published by OpenAI; omitted rather than guessed.
• parent: Not applicable — both are standalone models with no snapshots.
• multimodal: Not set. These are audio-focused models; the multimodal field is typically used for vision (image input) support in the catalog.

Local files inspected

• packages/proxy/schema/model_list.json — grep confirms neither gpt-realtime-translate nor gpt-realtime-whisper exists

Source URLs

• https://developers.openai.com/api/docs/models/gpt-realtime-translate
• https://developers.openai.com/api/docs/models/gpt-realtime-whisper
• https://developers.openai.com/api/docs/models
• https://openai.com/index/advancing-voice-intelligence-with-new-models-in-the-api/

{
  "kind": "missing_model",
  "provider": "openai",
  "models": ["gpt-realtime-translate", "gpt-realtime-whisper"],
  "status": "active",
  "model_specs": {
    "gpt-realtime-translate": {
      "format": "openai",
      "flavor": "chat",
      "max_input_tokens": 16000,
      "max_output_tokens": 2000,
      "available_providers": ["openai"]
    },
    "gpt-realtime-whisper": {
      "format": "openai",
      "flavor": "chat",
      "max_input_tokens": 16000,
      "max_output_tokens": 2000,
      "available_providers": ["openai"]
    }
  },
  "source_urls": [
    "https://developers.openai.com/api/docs/models/gpt-realtime-translate",
    "https://developers.openai.com/api/docs/models/gpt-realtime-whisper",
    "https://openai.com/index/advancing-voice-intelligence-with-new-models-in-the-api/"
  ]
}