Skip to main content
Glama

Agent Data Tools: Speech to text and text to speech

Dub audio: translated voice track in English or Spanish, plus subtitles

dub
Read-only

Dub a clip: speech in any of 90+ languages is transcribed, translated and spoken again as one MP3 in English or Spanish (Aura-2, pick a voice), with translated SRT on the original timings. MP3/WAV up to 10 minutes or other formats up to 2 MB, by URL or upload; up to 2,500 characters of new speech. The voice keeps the original order, not exact timing. Use for course clips, product videos and social posts in a second language. Example: url=https://upload.wikimedia.org/wikipedia/commons/7/77/Tofino_pronunciation.mp3, to=es. Price $0.10/call via x402 USDC or a card key (/credits); failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>",
      "to": "<to>"
    },
    "name": "dub"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesLanguage of the new voice: en or es
urlYesAbsolute http(s) URL of the recording (MP3/WAV up to 10 minutes; M4A, OGG or WebM up to 2 MB); or POST the file itself (raw body, multipart `file` part, or base64 in JSON)
fromNoSpoken language of the recording (default: detected)
voiceNoAura-2 voice for the new track (default luna for en, aquila for es)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations it discloses cost ($0.10/call via x402 USDC or card key, failed calls free), that repeats are not free (reinforcing the non-idempotent hint), and a quality caveat agents rarely get: the voice keeps the original order but not exact timing. It also adds the 2,500-character cap on new speech, which is not in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single dense paragraph, correctly front-loaded with what the tool does and what it returns before limits, pricing, and the example. Every clause carries information, though the format/size limits duplicate the schema and could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a paid, non-destructive media transformation with no output schema, the agent gets inputs and caps, both return artifacts (MP3 plus SRT on original timings), the pricing model, and the order-vs-timing caveat. Nothing material needed to call it correctly or predict the result is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% – formats, size limits, defaults for `from`/`voice`, and the en/es enum for `to` are all documented in the schema already, so the description largely restates them. It adds only one genuinely new constraint (up to 2,500 characters of new speech) and the 90+ source-language breadth, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Dub a clip: speech in any of 90+ languages is transcribed, translated and spoken again as one MP3 in English or Spanish ... with translated SRT" names a specific verb, the transformation pipeline, and both outputs. An agent can immediately distinguish this from siblings like ai_tts (speech only) or subtitles_translate (subtitles only) because the dual MP3+SRT output is stated up front.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use for course clips, product videos and social posts in a second language" gives concrete usage context, and a full example (url + to=es) shows a real invocation. It stops short of explicit exclusions or naming the sibling to pick when only subtitles or only a voice track are wanted, so the boundary with subtitles_translate / ai_tts is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.