/*
 * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
 */

import { llmSpeechTranscribe } from "../../funcs/llmSpeechTranscribe.js";
import * as operations from "../../models/operations/index.js";
import { formatResult, ToolDefinition } from "../tools.js";

const args = {
  request: operations.TranscribeRequest$inboundSchema,
};

export const tool$llmSpeechTranscribe: ToolDefinition<typeof args> = {
  name: "llm-speech-transcribe",
  description: `Speech to text transcription

Convert audio to text using advanced speech recognition.

**Complete File Upload (Standard)**
Use \`Content-Type: multipart/form-data\` to upload the complete audio file in one request. Maximum file size: 25MB.

Example:
\`\`\`bash
curl -X POST "http://localhost:3000/api/v1/llm/speech/transcriptions?language=en" \
  -F "file=@audio.flac"
\`\`\`

**Chunked Upload (Streaming)**
Use \`Transfer-Encoding: chunked\` header to stream audio data in chunks as it's being recorded. No need to know total file size upfront. Server buffers chunks until complete before processing. Maximum total size: 25MB.

Example:
\`\`\`bash
curl -X POST "http://localhost:3000/api/v1/llm/speech/transcriptions?language=en" \
  -H "Transfer-Encoding: chunked" \
  -H "Content-Type: multipart/form-data" \
  --data-binary @audio.flac
\`\`\`

**Supported Formats:** FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, WebM

**Query Parameters:**
- \`model\` (optional): Transcription model identifier. Defaults to 'auto'.
- \`language\` (optional): ISO-639-1 or BCP-47 language code (e.g., "en", "en-US"). Auto-detects if not specified.
- \`prompt\` (optional): Legacy prompt parameter retained for backward compatibility.
- \`temperature\` (optional): Legacy temperature parameter retained for backward compatibility.
- \`include_speaker_data\` (optional): When \`true\`, include speaker diarization data and require WAV/PCM input. Otherwise transcription uses the standard compatibility path.

**Response:** Returns transcribed text in JSON format.`,
  args,
  tool: async (client, args, ctx) => {
    const [result, apiCall] = await llmSpeechTranscribe(
      client,
      args.request,
      { fetchOptions: { signal: ctx.signal } },
    ).$inspect();

    if (!result.ok) {
      return {
        content: [{ type: "text", text: result.error.message }],
        isError: true,
      };
    }

    const value = result.value;

    return formatResult(value, apiCall);
  },
};