docs: add documentation about transcription uploads options#13
Conversation
Most options for the `/v1/transcript` endpoint to start a new transcription are undocumented. This patch adds documentation for all of the current request parameters.
Summary of ChangesHello @lkiesow, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the API documentation by detailing the various parameters available for the Highlights
Changelog
Activity
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds comprehensive documentation for the transcription endpoint parameters, which is a great improvement for usability. The new documentation is well-structured and aligns with the implementation. I've added a few suggestions to enhance the clarity of some of the more technical decoding parameters.
lkiesow
changed the title
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughThe PR adds a comprehensive "Parameters" section to README.md documenting API inputs across eight categories: Input, Language & Task, Speaker Diarization, Decoding, Timestamps & Alignment, VAD, Subtitle Formatting, and Webhook. Each category includes parameter tables with type, default value, and description details. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
🧹 Nitpick comments (2)
README.md (2)
248-254: Add a webhook security note near these parameters.Consider adding a brief note to prefer HTTPS endpoints and treat
webhook_auth_headeras a secret. This helps prevent accidental insecure deployments.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` around lines 248 - 254, Add a short security note next to the webhook parameters (`webhook_url`, `webhook_auth_header`) advising to use HTTPS endpoints and to treat `webhook_auth_header` as a secret (do not commit/store in plaintext), and suggest rotating credentials and validating payloads if possible; insert this note immediately after the Webhook table so readers see security guidance alongside the parameter definitions.
185-239: Document value ranges and key constraints for decoding/VAD parameters.The tables are comprehensive, but for several numeric fields users still won’t know valid bounds (for example 0–1 thresholds) or common constraints. Adding ranges/constraints here would reduce invalid requests and support churn.
📝 Suggested doc patch
**Decoding:** @@ | `temperature` | float | `0.0` | Sampling temperature (`0` = greedy decoding) | @@ | `no_speech_threshold` | float | `0.6` | If the no-speech probability is higher than this value, the segment is considered silent | @@ +Notes: +- `temperature`, `temperature_increment_on_fallback` should be non-negative. +- `no_speech_threshold` is typically in `[0.0, 1.0]` (higher = more aggressive silence filtering). +- `logprob_threshold` and `compression_ratio_threshold` are advanced filters; defaults are recommended unless tuning for a specific dataset. + **VAD (Voice Activity Detection):** @@ | `vad_onset` | float | `0.5` | VAD speech onset threshold | | `vad_offset` | float | `0.363` | VAD speech offset threshold | @@ +Notes: +- `vad_onset` / `vad_offset` are probability thresholds, typically in `[0.0, 1.0]`.🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@README.md` around lines 185 - 239, Add explicit valid ranges and key constraints for numeric and enumerated parameters shown (e.g., temperature, temperature_increment_on_fallback, beam_size, best_of, patience, length_penalty, logprob_threshold, compression_ratio_threshold, no_speech_threshold, vad_onset, vad_offset, chunk_size, speakers_expected/min_speakers/max_speakers, and boolean flags like word_timestamps/return_char_alignments); for each parameter include allowed type, min/max or accepted values (e.g., temperature 0.0–1.0, beam_size >=1, best_of >=1, patience >=0, compression_ratio_threshold >=1.0, logprob_threshold typically <=0, vad_onset/vad_offset in 0.0–1.0, chunk_size >0 and recommended max like 30s, segment_resolution ∈ {sentence, chunk}), note any inter-parameter constraints (e.g., max_speakers >= min_speakers, speakers_expected optional when diarization disabled), and mark defaults and recommended typical ranges to prevent invalid requests.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@README.md`:
- Around line 248-254: Add a short security note next to the webhook parameters
(`webhook_url`, `webhook_auth_header`) advising to use HTTPS endpoints and to
treat `webhook_auth_header` as a secret (do not commit/store in plaintext), and
suggest rotating credentials and validating payloads if possible; insert this
note immediately after the Webhook table so readers see security guidance
alongside the parameter definitions.
- Around line 185-239: Add explicit valid ranges and key constraints for numeric
and enumerated parameters shown (e.g., temperature,
temperature_increment_on_fallback, beam_size, best_of, patience, length_penalty,
logprob_threshold, compression_ratio_threshold, no_speech_threshold, vad_onset,
vad_offset, chunk_size, speakers_expected/min_speakers/max_speakers, and boolean
flags like word_timestamps/return_char_alignments); for each parameter include
allowed type, min/max or accepted values (e.g., temperature 0.0–1.0, beam_size
>=1, best_of >=1, patience >=0, compression_ratio_threshold >=1.0,
logprob_threshold typically <=0, vad_onset/vad_offset in 0.0–1.0, chunk_size >0
and recommended max like 30s, segment_resolution ∈ {sentence, chunk}), note any
inter-parameter constraints (e.g., max_speakers >= min_speakers,
speakers_expected optional when diarization disabled), and mark defaults and
recommended typical ranges to prevent invalid requests.
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Most options for the
/v1/transcriptendpoint to start a new transcription are undocumented. This patch adds documentation for all of the current request parameters.Summary by CodeRabbit