upgrade playht to latest engine

[purby]

trafficstars

This pull request implements the upgrade of the Play.ht synthesizer engine to the latest version, PlayHT2.0-turbo. Documentation for API Reference: https://docs.play.ht/reference/http-api-audio-streaming

[arpagon]

@CodiumAI-Agent /review

[CodiumAI-Agent]

PR Review

PR feedback
⏱️ Estimated effort to review [1-5]	3, because the PR involves changes to authentication headers, updates to API endpoints, and modifications to synthesizer configuration which require a careful review to ensure compatibility and correctness.
🧪 Relevant tests	No
🔍 Possible issues	The removal of the "Bearer" token prefix in the "AUTHORIZATION" header may lead to authentication failures if the Play.ht API still expects this format. Hardcoding the default voice and voice engine in the synthesizer configuration could reduce flexibility and make future updates more cumbersome.
🔒 Security concerns	No

Code feedback:

---

relevant file	tests/synthesizer/conftest.py
suggestion	Consider verifying if the Play.ht API has changed its authentication scheme to no longer require the "Bearer" token prefix. If it still requires the prefix, revert this change. [important]
relevant line	if headers["AUTHORIZATION"] != MOCK_API_KEY:

---

relevant file	vocode/streaming/models/synthesizer.py
suggestion	It's recommended to keep the flexibility of configuring the voice and voice engine externally, for example, through environment variables or configuration files, instead of hardcoding them. [medium]
relevant line	PLAYHT_DEFAULT_VOICE = "s3://peregrine-voices/mel28/manifest.json"

---

relevant file	vocode/streaming/synthesizer/play_ht_synthesizer.py
suggestion	Ensure the new API endpoint "https://api.play.ht/api/v2/tts/stream" is correct and fully compatible with the existing parameters and authentication method used in this synthesizer. [important]
relevant line	TTS_ENDPOINT = "https://api.play.ht/api/v2/tts/stream"

---

relevant file	vocode/streaming/synthesizer/play_ht_synthesizer.py
suggestion	Validate the "voice_engine" parameter compatibility with the Play.ht API. If this parameter is specific to the new engine version, ensure backward compatibility or document the change clearly. [medium]
relevant line	"voice_engine": self.synthesizer_config.voice_engine,

---

---

✨ Usage guide:

---

Overview: The review tool scans the PR code changes, and generates a PR review. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR. When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

Utilizing extra instructions The review tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize. Examples for extra instructions: [pr_reviewer] # /review # extra_instructions=""" In the 'possible issues' section, emphasize the following: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """ Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.

How to enable\disable automation When you first install PR-Agent app, the default mode for the review tool is: pr_commands = ["/review", ...] meaning the review tool will run automatically on every PR, with the default configuration. Edit this field to enable/disable the tool, or to change the used configurations

Auto-labels The review tool can auto-generate two specific types of labels for a PR: a possible security issue label, that detects possible security issues (enable_review_labels_security flag) a Review effort [1-5]: x label, where x is the estimated effort to review the PR (enable_review_labels_effort flag)

Extra sub-tools The review tool provides a collection of possible feedbacks about a PR. It is recommended to review the possible options, and choose the ones relevant for your use case. Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: require_score_review, require_soc2_ticket, and more.

Auto-approve PRs By invoking: /review auto_approve The tool will automatically approve the PR, and add a comment with the approval. To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following: [pr_reviewer] enable_auto_approval = true (this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository) You can also enable auto-approval only if the PR meets certain requirements, such as that the estimated_review_effort is equal or below a certain threshold, by adjusting the flag: [pr_reviewer] maximal_review_effort = 5

More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the review usage page for a comprehensive guide on using this tool.

[CodiumAI-Agent]

PR Analysis

• 🎯 Main theme: Upgrading the Play.ht synthesizer engine to the latest version
• 📝 PR summary: This PR updates the Play.ht synthesizer engine to the latest version, PlayHT2.0-turbo. It includes changes to the authorization headers, the TTS endpoint, and the voice engine parameters in the synthesizer configuration.
• 📌 Type of PR: Enhancement
• 🧪 Relevant tests added: No
• ⏱️ Estimated effort to review [1-5]: 2, because the changes are straightforward and limited to a few files, but they are critical to the functionality of the synthesizer.
• 🔒 Security concerns: Yes, because the API key is stored directly in the code, which could expose it if the code is publicly accessible.

PR Feedback

💡 General suggestions: The changes in this PR are clear and concise, focusing on the necessary updates for the Play.ht synthesizer engine. However, it would be beneficial to include tests that verify the new functionality and ensure that the changes do not introduce regressions.

🤖 Code feedback:

---

relevant file	tests/synthesizer/conftest.py
suggestion	Consider using a more secure method for storing and accessing sensitive data like API keys. Storing sensitive data in code can lead to security vulnerabilities. [important]
relevant line	if headers["AUTHORIZATION"] != MOCK_API_KEY:

---

relevant file	vocode/streaming/models/synthesizer.py
suggestion	It would be better to store the default voice and voice engine as environment variables or in a configuration file. This would make it easier to update these values without having to modify the code. [medium]
relevant line	PLAYHT_DEFAULT_VOICE = "s3://peregrine-voices/mel28/manifest.json"

---

relevant file	vocode/streaming/synthesizer/play_ht_synthesizer.py
suggestion	Consider validating the input parameters before making the API request. This can help catch errors early and make debugging easier. [medium]
relevant line	"voice_engine": self.synthesizer_config.voice_engine,

---

---

✨ Usage guide:

---

Overview: The review tool scans the PR code changes, and generates a PR review. The tool can be triggered automatically every time a new PR is opened, or can be invoked manually by commenting on any PR. When commenting, to edit configurations related to the review tool (pr_reviewer section), use the following template:

/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...

With a configuration file, use the following template:

[pr_reviewer]
some_config1=...
some_config2=...

Utilizing extra instructions The review tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project. Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize. Examples for extra instructions: [pr_reviewer] # /review # extra_instructions=""" In the code feedback section, emphasize the following: - Does the code logic cover relevant edge cases? - Is the code logic clear and easy to understand? - Is the code logic efficient? ... """ Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.

How to enable\disable automation When you first install PR-Agent app, the default mode for the review tool is: pr_commands = ["/review", ...] meaning the review tool will run automatically on every PR, with the default configuration. Edit this field to enable/disable the tool, or to change the used configurations

About the 'Code feedback' section The review tool provides several type of feedbacks, one of them is code suggestions. If you are interested only in the code suggestions, it is recommended to use the improve feature instead, since it dedicated only to code suggestions, and usually gives better results. Use the review tool if you want to get a more comprehensive feedback, which includes code suggestions as well.

Auto-labels The review tool can auto-generate two specific types of labels for a PR: a possible security issue label, that detects possible security issues (enable_review_labels_security flag) a Review effort [1-5]: x label, where x is the estimated effort to review the PR (enable_review_labels_effort flag)

Extra sub-tools The review tool provides a collection of possible feedbacks about a PR. It is recommended to review the possible options, and choose the ones relevant for your use case. Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: require_score_review, require_soc2_review, enable_review_labels_effort, and more.

More PR-Agent commands To invoke the PR-Agent, add a comment using one of the following commands: /review: Request a review of your Pull Request. /describe: Update the PR title and description based on the contents of the PR. /improve [--extended]: Suggest code improvements. Extended mode provides a higher quality feedback. /ask <QUESTION>: Ask a question about the PR. /update_changelog: Update the changelog based on the PR's contents. /add_docs 💎: Generate docstring for new components introduced in the PR. /generate_labels 💎: Generate labels for the PR based on the PR's contents. /analyze 💎: Automatically analyzes the PR, and presents changes walkthrough for each component. See the tools guide for more details. To list the possible configuration parameters, add a /config comment.

See the review usage page for a comprehensive guide on using this tool.

[ajar98]

hi @purby we built support for play.ht's V2 API in the newest version! https://docs.vocode.dev/open-source/using-synthesizers#play-ht-v2