Tanod MCP server

mlpeek: text to speech (6 languages, offline)

text_to_speech

Idempotent

Convert text into spoken audio in 41 voices across six languages. Use it for voiceovers, accessibility, or audio versions of written content.

Instructions

mlpeek: Speak text aloud in 41 voices: English, Spanish, French, Hindi, Italian, Portuguese. For audio to text use transcribe_audio. Returns the text spoken as audio. Offline neural TTS (Kokoro-82M); the audio is a synthetic voice. At most 2,000 characters; 41 voices in 6 languages (the voice sets the language: write the text in it). Bad input is a 422, a busy or unavailable model a 503, a synthesis over the time limit a 504 (none charged). Save data_base64 to a file to play it, or send output "url" for a 24 h link. Typically 4-10 s for 200 characters (about 13 s of speech), up to about a minute for 2,000 characters. Price: USD 0.005. Free: 5 mlpeek calls per IP per UTC day. The submitted text is not logged; the result is kept only with output "url" (24 h). Docs: https://tanod.dev/learn/text-to-speech-api.html

Input Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	Text to speak, 1 to 2,000 characters, in the language of the chosen voice (English, Spanish, French, Hindi, Italian or Brazilian Portuguese).
`speed`	No	Speaking rate, 0.5 to 2.0 (1.0 is normal).
`voice`	No	Voice (41): the first letter is the language: a US English (af_heart default, af_bella, am_adam), b UK English (bf_emma, bm_george), e Spanish (ef_dora), f French (ff_siwis), h Hindi (hf_alpha, hm_omega), i Italian (if_sara, im_nicola), p Brazilian Portuguese (pf_dora, pm_alex); f = female, m = male. Write the text in the voice's language.	af_heart
`format`	No	Audio format: mp3, wav (16-bit PCM) or ogg (Opus).	mp3
`output`	No	base64 (default): the file comes back inline as base64. url: the file is stored for 24 hours and the reply carries a download link (url, expires_at, bytes, content_type, sha256) instead of the base64, which keeps the file out of your context window.	base64

Output Schema

TableJSON Schema

Name	Required	Description
`url`	No
`bytes`	No
`chars`	No
`error`	No	Only on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
`speed`	No
`voice`	No
`engine`	No
`format`	No
`sha256`	No
`duration_s`	No
`expires_at`	No
`data_base64`	No
`sample_rate`	No
`content_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 15, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Goes well beyond the annotations with pricing (USD 0.005), a free tier (5 calls per IP per UTC day), latency expectations (4-10 s for 200 chars, ~1 min for 2,000), retention/privacy (text not logged; result kept only with output=url for 24 h), and error mapping (422/503/504, none charged). This is rich behavioral disclosure. Minor ding: it does not clarify why readOnlyHint=false for what is effectively a compute-only call, and gives no guidance on what happens to an in-flight job on timeout.

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?

Front-loaded with purpose and the sibling alternative, which is the right priority. However it is a dense single paragraph that repeats '41 voices' and '6 languages' (already in the title), and error codes, pricing, latency, and retention are interleaved rather than grouped, costing some scanability.

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?

With an output schema present, the description need not explain return values, and it still covers limits, cost, latency, privacy, retention, and failure modes. Nothing an agent needs in order to call this correctly (language/voice coupling, size cap, output mode) 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% and three params have enums, so the schema already documents text limits, speed range, format, output semantics, and the voice-language mapping. The description largely restates these (2000-char cap, voices set the language, url keeps the file out of context) rather than adding new parameter meaning. Baseline 3 is appropriate.

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?

States a specific verb+resource (speak text aloud / TTS) with concrete scope: 41 voices, 6 named languages, offline Kokoro-82M. It explicitly distinguishes itself from the reverse-direction sibling by naming transcribe_audio, so an agent can separate them without opening either schema.

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

Usage Guidelines5/5

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

Gives an explicit alternative with its selecting condition ('For audio to text use transcribe_audio'), plus conditional guidance for the output param (save base64 to a file, or request a 24 h url). It also tells the user to write the text in the voice's language, which is the key correctness condition.

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

Deploy Server