Skip to content

feat(inputTranscription): add support for gpt-4o-transcribe & gpt-4o-mini-transcribe models, plus language & prompt parameters #134

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

feat(inputTranscription): add support for gpt-4o-transcribe & gpt-4o-mini-transcribe models, plus language & prompt parameters #134

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5b6912f
Added Input Audio Model Support
HVbajoria May 22, 2025
a62c334
Updated Readme.md
HVbajoria May 24, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,9 @@ An example `session.update` that configures several aspects of the session, incl
"instructions": "Call provided tools if appropriate for the user's input.",
"input_audio_format": "pcm16",
"input_audio_transcription": {
"model": "whisper-1"
"model": "whisper-1", // We can also choose from "gpt-4o-mini-transcribe" or "gpt-4o-transcribe"
"language": "en", // optional language (ISO-639-1 format)
"prompt":"words you can expect in the input" // optional
},
"turn_detection": {
"threshold": 0.4,
Expand Down
4 changes: 3 additions & 1 deletion javascript/standalone/src/models.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,9 @@ export type ToolChoice = "auto" | "none" | "required" | FunctionToolChoice;
export type MessageRole = "system" | "assistant" | "user";

export interface InputAudioTranscription {
model: "whisper-1";
model: "whisper-1" | "gpt-4o-mini-transcribe" | "gpt-4o-transcribe";
language?: string;
prompt?: string;
}

export interface ClientMessageBase {
Expand Down
4 changes: 3 additions & 1 deletion python/rtclient/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,9 @@ class FunctionToolChoice(ModelWithDefaults):


class InputAudioTranscription(BaseModel):
model: Literal["whisper-1"]
model: Literal["whisper-1", "gpt-4o-mini-transcribe", "gpt-4o-transcribe"]
language: Optional[str] = None
prompt: Optional[str] = None


class ClientMessageBase(ModelWithDefaults):
Expand Down