What makes gladia-pre-recorded-transcription notable?

959 downloads. Trust evidence available

How should gladia-pre-recorded-transcription be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

gladia-pre-recorded-transcription

Transcribe pre-recorded audio files or URLs with Gladia. Use when the user needs batch/async transcription, speaker diarization, subtitles (SRT/VTT), PII redaction, translation, NER, summarization, audio-to-LLM, or any audio intelligence on pre-recorded content. Always prefer the official SDK; fall back to raw REST only when SDK cannot satisfy the requirement.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

959

Updated

Oct 12, 2026

Version

1.0.3

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 959 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 959 downloadsadoption · observed Oct 12, 2026
Latest release: 1.0.3release · observed Oct 2, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.3release
- Documentation updates: minor edits to SKILL.md and references/transcription-options.md for clarity and accuracy. - Internal cleanup: removed the obsolete skill-card.md file.
Observed Oct 2, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s170451ybbxgxcc4es3g96b4fs8823td:gladia-pre-recorded-transcription

Install using `clawhub skill install s170451ybbxgxcc4es3g96b4fs8823td:gladia-pre-recorded-transcription` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/gladiaio/gladia-pre-recorded-transcription before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-gladiaio-gladia-pre-recorded-transcription/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

80,708 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: gladia-pre-recorded-transcription
description: Transcribe pre-recorded audio files or URLs with Gladia. Use when the user needs batch/async transcription, speaker diarization, subtitles (SRT/VTT), PII redaction, translation, NER, summarization, audio-to-LLM, or any audio intelligence on pre-recorded content. Always prefer the official SDK; fall back to raw REST only when SDK cannot satisfy the requirement.
license: MIT
---

# Pre-Recorded Transcription

Gladia's pre-recorded API transcribes audio and video files asynchronously.

> **SDK-first**: always use the official SDK — see [gladia-sdk-integration](../gladia-sdk-integration/SKILL.md) for policy, setup, and fallback criteria.

## When to Use

- Existing audio/video files or URLs (including social/video links)
- Batch or asynchronous transcription workflows
- Pre-recorded-only features: diarization, PII redaction, subtitles

**When NOT to use:** If the user needs real-time / live transcription of a stream, microphone, or ongoing audio feed, use the [gladia-live-transcription skill](../gladia-live-transcription/SKILL.md) instead. Live transcription uses WebSocket sessions, not the pre-recorded API. If the user has gladia-cli installed and wants a quick terminal workflow without writing code, use [gladia-using-cli](../gladia-using-cli/SKILL.md) instead.

## References

Consult these resources as needed:

- ./references/transcription-options.md -- Full options (JS + Python)
- ./references/managing-jobs.md -- `get`, `list`, `getFile`, `delete`
- ./references/delivery-and-response.md -- Response shape and events
- ../gladia-audio-intelligence/SKILL.md -- Feature availability and config
- ../gladia-using-cli/SKILL.md -- Terminal workflow with gladia-cli
- ../gladia-sdk-integration/SKILL.md -- Setup, config, SDK vs raw API
- ../gladia-sdk-integration/references/sdk-versions.md -- Current SDK versions
- ../gladia-troubleshooting/SKILL.md -- Errors and diagnostics

## API Endpoints (reference — prefer SDK methods instead)

| Endpoint                    | Method | SDK equivalent                          |
| --------------------------- | ------ | --------------------------------------- |
| `/v2/upload`                | POST   | `transcribe()` auto-uploads local files |
| `/v2/pre-recorded`          | POST   | `create()` / `transcribe()`             |
| `/v2/pre-recorded`          | GET    | `list()`                                |
| `/v2/pre-recorded/:id`      | GET    | `get()` / `poll()` / `transcribe()`     |
| `/v2/pre-recorded/:id`      | DELETE | `delete()`                              |
| `/v2/pre-recorded/:id/file` | GET    | `getFile()`                             |

## Workflow

### Recommended (SDK)

The SDK `transcribe()` method handles upload, job creation, and polling in one call. Use this by default.

```typescript
const result = await client.preRecorded().transcribe("./audio.mp3", {
  language_config: { languages: ["en"] },
  diarization: true,
});

console.log(result.result?.t

_meta.json

{
  "ownerId": "kn7fs6cmj9hqg7232sbkacf31d882wp2",
  "slug": "gladia-pre-recorded-transcription",
  "version": "1.0.3",
  "publishedAt": 1790953650699
}

references/delivery-and-response.md

# Delivery and Response Reference

Reference for the pre-recorded job response shape and asynchronous delivery events.

## Contents

- Response Structure
- Callback Events
- Webhook Events

## Response Structure

```json
{
  "id": "job-uuid",
  "status": "done",
  "result": {
    "transcription": {
      "full_transcript": "Hello, welcome to the meeting...",
      "utterances": [
        {
          "text": "Hello, welcome to the meeting",
          "language": "en",
          "start": 0.5,
          "end": 2.1,
          "speaker": 0,
          "words": [{ "word": "Hello", "start": 0.5, "end": 0.8, "confidence": 0.98 }]
        }
      ]
    },
    "diarization": {},
    "translation": {},
    "summarization": {},
    "sentiment_analysis": {}
  }
}
```

## Callback Events

Callbacks are sent to the `callback_url` in your transcription request body:

- `transcription.success` — job completed successfully
- `transcription.error` — job failed

## Webhook Events

Webhooks are configured in Dashboard -> Account -> Webhooks:

- `transcription.created` — job queued
- `transcription.success` — job completed
- `transcription.error` — job failed

Webhooks are powered by Svix with signed requests for verification.

references/managing-jobs.md

# Managing Pre-Recorded Jobs

Reference for retrieving, listing, downloading, and deleting pre-recorded transcription jobs.

## Contents

- Get a Single Job
- List Jobs
- List Query Parameters
- Download Original Audio
- Delete a Job

## Get a Single Job

Fetch the status and full result payload for one job:

```typescript
const job = await client.preRecorded().get(jobId);
console.log(job.status); // "queued" | "processing" | "done" | "error"
console.log(job.result?.transcription?.full_transcript);
```

```python
job = client.prerecorded().get(job_id)
print(job.status)
print(job.result.transcription.full_transcript)
```

Raw REST: `GET /v2/pre-recorded/:id`

## List Jobs

Retrieve jobs with optional filters. The response is paginated.

```typescript
const page = await client.preRecorded().list({
  offset: 0,
  limit: 20,
  status: ["done"],
  after_date: "2026-01-01T00:00:00Z",
  before_date: "2026-06-01T00:00:00Z",
  custom_metadata: { userId: "abc123" },
});

for (const job of page.items) {
  console.log(job.id, job.status);
}

// page.next is the URL for the next page (null when last page)
```

```python
page = client.prerecorded().list(
    offset=0,
    limit=20,
    status=["done"],
    after_date="2026-01-01T00:00:00Z",
    before_date="2026-06-01T00:00:00Z",
    custom_metadata={"userId": "abc123"},
)

for job in page.items:
    print(job.id, job.status)
```

Raw REST: `GET /v2/pre-recorded`

## List Query Parameters

| Parameter         | Type     | Description                                                 |
| ----------------- | -------- | ----------------------------------------------------------- |
| `offset`          | integer  | Pagination start (default `0`)                              |
| `limit`           | integer  | Max items per page (default `20`, min `1`)                  |
| `date`            | string   | Filter to a specific day (`YYYY-MM-DD`)                     |
| `before_date`     | string   | Jobs created before this ISO 8601 datetime                  |
| `after_date`      | string   | Jobs created after this ISO 8601 datetime                   |
| `status`          | string[] | Filter by status: `queued`, `processing`, `done`, `error`   |
| `custom_metadata` | object   | Filter by metadata key/value pairs attached at job creation |

Pagination fields in the response:

- `first` (URL)
- `current` (URL)
- `next` (URL or `null`)
- `items` (array)

## Download Original Audio

Download the original audio used for transcription:

```typescript
const audioBlob = await client.preRecorded().getFile(jobId);
```

```python
audio_bytes = client.prerecorded().get_file(job_id)
```

Raw REST: `GET /v2/pre-recorded/:id/file`

## Delete a Job

Delete a job and associated data:

```typescript
await client.preRecorded().delete(jobId);
```

```python
client.prerecorded().delete(job_id)
```

Raw REST: `DELETE /v2/pre-recorded/:id`

references/transcription-options.md

# Transcription Options Reference

Complete configuration reference for all pre-recorded transcription options passed as the second argument to `transcribe()`.

## Contents

- Language Configuration
- Audio Intelligence Options (full example)
- Delivery (callbacks)

For client-level config (retry, timeouts, HTTP headers), see [gladia-sdk-integration](../../gladia-sdk-integration/SKILL.md#configuration-options). For detailed audio intelligence feature docs, see [gladia-audio-intelligence](../../gladia-audio-intelligence/SKILL.md).

## Full Options Example (JavaScript/TypeScript)

```typescript
const result = await client.preRecorded().transcribe(audioInput, {
  // Language
  language_config: {
    languages: ["en", "fr"], // Expected languages (ISO 639-1)
    code_switching: true, // Detect language changes mid-speech
  },

  // Audio Intelligence
  diarization: true, // Speaker identification
  diarization_config: { number_of_speakers: 3 },
  translation: true,
  translation_config: { target_languages: ["fr", "es"] },
  summarization: true,
  summarization_config: { type: "bullet_points" },
  sentiment_analysis: true,
  named_entity_recognition: true,
  subtitles: true,
  subtitles_config: { formats: ["srt", "vtt"] },
  pii_redaction: true,
  pii_redaction_config: {
    policy: "mask",
    entities: ["person", "location", "phone_number"],
  },
  audio_to_llm: true,
  audio_to_llm_config: { prompts: ["Summarize the key decisions made"] },
  custom_vocabulary: true,
  custom_vocabulary_config: {
    vocabulary: [
      { value: "Gladia", intensity: 0.5 },
      { value: "Kubernetes", pronunciations: ["koo-ber-net-eez"] },
    ],
  },

  // Delivery
  callback_url: "https://your-server.com/webhook",
});
```

## Full Options Example (Python)

```python
result = client.prerecorded().transcribe("audio.mp3", {
    "language_config": {"languages": ["en", "fr"], "code_switching": True},
    "diarization": True,
    "diarization_config": {"number_of_speakers": 3},
    "translation": True,
    "translation_config": {"target_languages": ["fr", "es"]},
    "summarization": True,
    "summarization_config": {"type": "bullet_points"},
    "sentiment_analysis": True,
    "named_entity_recognition": True,
    "subtitles": True,
    "subtitles_config": {"formats": ["srt", "vtt"]},
    "pii_redaction": True,
    "pii_redaction_config": {"policy": "mask", "entities": ["person", "location", "phone_number"]},
    "audio_to_llm": True,
    "audio_to_llm_config": {"prompts": ["Summarize the key decisions made"]},
    "custom_vocabulary": True,
    "custom_vocabulary_config": {
        "vocabulary": [
            {"value": "Gladia", "intensity": 0.5},
            {"value": "Kubernetes", "pronunciations": ["koo-ber-net-eez"]},
        ],
    },
    "callback_url": "https://your-server.com/webhook",
})
```

## Options Quick Reference

| Option                                  | Type       | Description                             |
| ---------------------------------------

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular