Add create audio speech stream support #188
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
SunburstEnzo
suggested changes
Mar 30, 2024
Sources/OpenAI/OpenAI.swift
Outdated
| organizationIdentifier: configuration.organizationIdentifier, | ||
| timeoutInterval: configuration.timeoutInterval) | ||
| let session = StreamingSession<AudioSpeechResult>(urlRequest: request) | ||
| session.onReceiveContent = {_, object in |
There was a problem hiding this comment.
Suggested change
| session.onReceiveContent = {_, object in | |
| session.onReceiveContent = { _, object in |
Sources/OpenAI/OpenAI.swift
Outdated
| session.onReceiveContent = {_, object in | ||
| onResult(.success(object)) | ||
| } | ||
| session.onProcessingError = {_, error in |
There was a problem hiding this comment.
Suggested change
| session.onProcessingError = {_, error in | |
| session.onProcessingError = { _, error in |
| query: AudioSpeechQuery | ||
| ) -> AsyncThrowingStream<AudioSpeechResult, Error> { | ||
| return AsyncThrowingStream { continuation in | ||
| return audioCreateSpeechStream(query: query) { result in |
There was a problem hiding this comment.
Suggested change
| return audioCreateSpeechStream(query: query) { result in | |
| return audioCreateSpeechStream(query: query) { result in |
| Example: | ||
| ``` | ||
| let query = AudioSpeechQuery(model: .tts_1, input: "Hello, world!", voice: .alloy, responseFormat: .mp3, speed: 1.0) | ||
| openAI.audioCreateSpeech(query: query) { result in |
There was a problem hiding this comment.
Suggested change
| openAI.audioCreateSpeech(query: query) { result in | |
| openAI.audioCreateSpeechStream(query: query) { result in |
Don't forget to change the docs
|
@SunburstEnzo Thanks for the comments! PR updated |
|
|
Closing this PR as new PR with the same changes was opened: |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What
OpenAI supports sending audio speech by chunks (see my issue here: #185). This PR adds support for this feature.
Why
With this change, clients can start audio playback with less latency, as far as first audio chunk will be received.
Affected Areas
In
OpenAIProtocolwas added new methodaudioCreateSpeechStream