microsoft/semantic-kernel · error · NotSupportedException

The format '{format}' is not supported.

Error message

The format '{format}' is not supported.

What it means

The audio output format string is matched case-insensitively against a fixed set (WAV, MP3, OPUS, FLAC, AAC, PCM). A null format is allowed (returns nulls, letting the API pick its default), but any non-null unrecognized string throws NotSupportedException. This check runs before the HTTP request is made.

Source

Thrown at dotnet/src/Connectors/Connectors.OpenAI/Core/ClientCore.TextToAudio.cs:71

            "FABLE" => GeneratedSpeechVoice.Fable,
            "ONYX" => GeneratedSpeechVoice.Onyx,
            "NOVA" => GeneratedSpeechVoice.Nova,
            "SHIMMER" => GeneratedSpeechVoice.Shimmer,
            _ => throw new NotSupportedException($"The voice '{voice}' is not supported."),
        };

    private static (GeneratedSpeechFormat? Format, string? MimeType) GetGeneratedSpeechFormatAndMimeType(string? format)
    {
        switch (format?.ToUpperInvariant())
        {
            case "WAV": return (GeneratedSpeechFormat.Wav, "audio/wav");
            case "MP3": return (GeneratedSpeechFormat.Mp3, "audio/mpeg");
            case "OPUS": return (GeneratedSpeechFormat.Opus, "audio/opus");
            case "FLAC": return (GeneratedSpeechFormat.Flac, "audio/flac");
            case "AAC": return (GeneratedSpeechFormat.Aac, "audio/aac");
            case "PCM": return (GeneratedSpeechFormat.Pcm, "audio/l16");
            case null: return (null, null);
            default: throw new NotSupportedException($"The format '{format}' is not supported.");
        }
    }
}

View on GitHub (pinned to c028a0c7dc)

Solutions

1. Use one of: wav, mp3, opus, flac, aac, pcm (case-insensitive).
2. Leave the format unset/null to let the API use its default if you don't need a specific container.
3. If you need a format outside this set (e.g. OGG), call the underlying OpenAI SDK directly.

Example fix

// before
var settings = new OpenAITextToAudioExecutionSettings { GeneratedSpeechFormat = "audio/mpeg" };

// after
var settings = new OpenAITextToAudioExecutionSettings { GeneratedSpeechFormat = "mp3" };

static readonly HashSet<string> SupportedFormats = new(StringComparer.OrdinalIgnoreCase)
{
    "wav", "mp3", "opus", "flac", "aac", "pcm"
};

void ValidateFormat(string? format)
{
    if (format is not null && !SupportedFormats.Contains(format.Trim()))
        throw new ArgumentOutOfRangeException(nameof(format),
            $"Format must be one of: {string.Join(", ", SupportedFormats)} (or null for default)");
}

try { var audio = await ttsService.GetAudioContentAsync(text, settings); }
catch (NotSupportedException ex) when (ex.Message.Contains("format"))
{
    settings.GeneratedSpeechFormat = null; // let API choose default
    var audio = await ttsService.GetAudioContentAsync(text, settings);
}

When it happens

Trigger: Passing OpenAITextToAudioExecutionSettings.GeneratedSpeechFormat (or equivalent) a value like 'ogg', 'webm', or a MIME-type string such as 'audio/mpeg' that does not match the allowed tokens.

Common situations: Confusing the format token with a MIME type or file extension (e.g. 'mp3 ' vs 'mp3'). Requesting a format the connector version doesn't map. Copying a format value from a different SDK's docs.

Related errors

• The voice '{voice}' is not supported.
• {type(self)} service failed to generate audio
• Invalid choice
• Invalid kernel selection. {selectedKernelName} is not a vali
• Unsupported image format.

AI-assisted analysis of microsoft/semantic-kernel@c028a0c7dc (2026-08-13). Data as JSON: /api/errors/ec720c52057a17d7. Report an issue: GitHub.