feat(api): new models for TTS, STT, + new audio features for Realtime (#298)

Author: stainless-app[bot]

Diff for: .stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 76
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-b26121d5df6eb5d3032a45a267473798b15fcfec76dd44a3256cf1238be05fa4.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-c22f59c66aec7914b6ee653d3098d1c1c8c16c180d2a158e819c8ddbf476f74b.yml

Diff for: api.md

@@ -145,9 +145,16 @@ Params Types:
 
 ## Transcriptions
 
+Params Types:
+
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#TranscriptionInclude">TranscriptionInclude</a>
+
 Response Types:
 
 - <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#Transcription">Transcription</a>
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#TranscriptionStreamEvent">TranscriptionStreamEvent</a>
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#TranscriptionTextDeltaEvent">TranscriptionTextDeltaEvent</a>
+- <a href="https://pkg.go.dev/github.com/openai/openai-go">openai</a>.<a href="https://pkg.go.dev/github.com/openai/openai-go#TranscriptionTextDoneEvent">TranscriptionTextDoneEvent</a>
 
 Methods:
 

Diff for: audio.go

@@ -34,11 +34,14 @@ func NewAudioService(opts ...option.RequestOption) (r *AudioService) {
 type AudioModel = string
 
 const (
-	AudioModelWhisper1 AudioModel = "whisper-1"
+	AudioModelWhisper1            AudioModel = "whisper-1"
+	AudioModelGPT4oTranscribe     AudioModel = "gpt-4o-transcribe"
+	AudioModelGPT4oMiniTranscribe AudioModel = "gpt-4o-mini-transcribe"
 )
 
 // The format of the output, in one of these options: `json`, `text`, `srt`,
-// `verbose_json`, or `vtt`.
+// `verbose_json`, or `vtt`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`,
+// the only supported format is `json`.
 type AudioResponseFormat string
 
 const (

Diff for: audiospeech.go

@@ -43,21 +43,25 @@ func (r *AudioSpeechService) New(ctx context.Context, body AudioSpeechNewParams,
 type SpeechModel = string
 
 const (
-	SpeechModelTTS1   SpeechModel = "tts-1"
-	SpeechModelTTS1HD SpeechModel = "tts-1-hd"
+	SpeechModelTTS1         SpeechModel = "tts-1"
+	SpeechModelTTS1HD       SpeechModel = "tts-1-hd"
+	SpeechModelGPT4oMiniTTS SpeechModel = "gpt-4o-mini-tts"
 )
 
 type AudioSpeechNewParams struct {
 	// The text to generate audio for. The maximum length is 4096 characters.
 	Input param.Field[string] `json:"input,required"`
 	// One of the available [TTS models](https://platform.openai.com/docs/models#tts):
-	// `tts-1` or `tts-1-hd`
+	// `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
 	Model param.Field[SpeechModel] `json:"model,required"`
 	// The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
 	// `coral`, `echo`, `fable`, `onyx`, `nova`, `sage` and `shimmer`. Previews of the
 	// voices are available in the
 	// [Text to speech guide](https://platform.openai.com/docs/guides/text-to-speech#voice-options).
 	Voice param.Field[AudioSpeechNewParamsVoice] `json:"voice,required"`
+	// Control the voice of your generated audio with additional instructions. Does not
+	// work with `tts-1` or `tts-1-hd`.
+	Instructions param.Field[string] `json:"instructions"`
 	// The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`,
 	// `wav`, and `pcm`.
 	ResponseFormat param.Field[AudioSpeechNewParamsResponseFormat] `json:"response_format"`

Diff for: audiospeech_test.go

@@ -30,6 +30,7 @@ func TestAudioSpeechNewWithOptionalParams(t *testing.T) {
 		Input:          openai.F("input"),
 		Model:          openai.F(openai.SpeechModelTTS1),
 		Voice:          openai.F(openai.AudioSpeechNewParamsVoiceAlloy),
+		Instructions:   openai.F("instructions"),
 		ResponseFormat: openai.F(openai.AudioSpeechNewParamsResponseFormatMP3),
 		Speed:          openai.F(0.250000),
 	})