Added a configurable Opus bitrate for audio transcription (#981)
Build and Release / Determine run mode (push) Waiting to run
Build and Release / Read metadata (push) Blocked by required conditions
Build and Release / Sync Flatpak repo (push) Blocked by required conditions
Build and Release / Collect Flatpak artifacts (push) Blocked by required conditions
Build and Release / Verify (push) Waiting to run
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-aarch64-apple-darwin, osx-arm64, macos-latest, aarch64-apple-darwin, dmg,app,updater, dmg) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-aarch64-pc-windows-msvc.exe, win-arm64, windows-latest, aarch64-pc-windows-msvc, nsis,updater, nsis) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-aarch64-unknown-linux-gnu, linux-arm64, ubuntu-22.04-arm, aarch64-unknown-linux-gnu, appimage,updater, appimage) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-x86_64-apple-darwin, osx-x64, macos-latest, x86_64-apple-darwin, dmg,app,updater, dmg) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-x86_64-pc-windows-msvc.exe, win-x64, windows-latest, x86_64-pc-windows-msvc, nsis,updater, nsis) (push) Blocked by required conditions
Build and Release / Build app (${{ matrix.dotnet_runtime }}) (-x86_64-unknown-linux-gnu, linux-x64, ubuntu-22.04, x86_64-unknown-linux-gnu, appimage,updater, appimage) (push) Blocked by required conditions
Build and Release / Prepare & create release (push) Blocked by required conditions
Build and Release / Publish release (push) Blocked by required conditions

Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>
This commit is contained in:
Dominic NeuburgandThorsten Sommer authored and GitHub committed 2026-09-19 19:13:33 +02:00
1 parent f9c6075c50
commit 1379ff6aab
19 files changed
+304 -23

No files matched your search

@@ -398,6 +398,9 @@ public sealed class PluginConfiguration(bool isInternal, LuaState state, PluginT
// Config: transcription provider?
ManagedConfiguration.TryProcessConfiguration(x => x.App, x => x.UseTranscriptionProvider, Guid.Empty, this.Id, settingsTable, dryRun);
// Config: transcription Opus bitrate?
ManagedConfiguration.TryProcessConfiguration(x => x.App, x => x.OpusBitrate, this.Id, settingsTable, dryRun);
message = string.Empty;
return true;
}
@@ -4,4 +4,5 @@ namespace AIStudio.Tools.Rust;
/// <param name="InputPath">Absolute source media path.</param>
/// <param name="OutputPath">Absolute operation-owned output path.</param>
/// <param name="MaxPassThroughBytes">Optional pass-through size ceiling.</param>
public sealed record CreateMediaJobRequest(string InputPath, string OutputPath, ulong? MaxPassThroughBytes = null);
/// <param name="OpusBitrateBps">Optional target Opus encoder bitrate in bits per second.</param>
public sealed record CreateMediaJobRequest(string InputPath, string OutputPath, ulong? MaxPassThroughBytes = null, uint? OpusBitrateBps = null);
@@ -1,6 +1,7 @@
using AIStudio.Chat;
using AIStudio.Provider;
using AIStudio.Settings;
using AIStudio.Settings.DataModel;
using AIStudio.Tools.Media;
using AIStudio.Tools.PluginSystem;
using AIStudio.Tools.Rust;
@@ -646,9 +647,23 @@ public sealed class MediaTranscriptionService(
MediaOperation operation,
bool updateImportState)
{
// The bitrate governs re-encoding, not every upload: the runtime hands a file through
// unchanged when it already is a single mono 48 kHz Opus track in a WebM container and small
// enough. Such a file keeps whatever bitrate it was made with, which is the better outcome --
// re-encoding it could only take quality away, never add any.
var opusBitrateBps = settingsManager.ConfigurationData.App.OpusBitrate.GetBitsPerSecond();
// Which quality an upload was produced with is the first question to ask when a transcript
// comes back missing something, so it has to be in the log of the job it belongs to:
logger.LogInformation(
"Normalizing media for operation {OperationId}; re-encoding uses the Opus bitrate {OpusBitrate} ({OpusBitrateBps} bps).",
operation.Id,
settingsManager.ConfigurationData.App.OpusBitrate,
opusBitrateBps);
// The quick POST is intentionally not cancelled: losing its response could orphan a job
// whose ID the client never received. Cancellation is applied immediately after ownership.
var jobId = await rustService.StartMediaJobAsync(mediaPath, normalizedPath, CancellationToken.None);
var jobId = await rustService.StartMediaJobAsync(mediaPath, normalizedPath, opusBitrateBps, CancellationToken.None);
operation.JobId = jobId;
try
@@ -10,13 +10,14 @@ public partial class RustService
/// <summary>Starts a Rust media normalization job.</summary>
/// <param name="inputPath">Absolute source path.</param>
/// <param name="outputPath">Absolute operation-owned output path.</param>
/// <param name="opusBitrateBps">Target Opus encoder bitrate in bits per second.</param>
/// <param name="token">Request cancellation token.</param>
/// <returns>The opaque runtime job identifier.</returns>
public async Task<string> StartMediaJobAsync(string inputPath, string outputPath, CancellationToken token = default)
public async Task<string> StartMediaJobAsync(string inputPath, string outputPath, uint opusBitrateBps, CancellationToken token = default)
{
using var response = await this.http.PostAsJsonAsync(
"/media/jobs",
new CreateMediaJobRequest(inputPath, outputPath),
new CreateMediaJobRequest(inputPath, outputPath, OpusBitrateBps: opusBitrateBps),
this.jsonRustSerializerOptions,
token);