Skip to main content
Glama
unifically-dev

UnificAlly MCP Server

Official
by unifically-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Generate audio

generate_audio
Destructive

Generate text-to-speech, sound effects, multi-voice dialogue, transcripts, voice changes, or cleaned audio from text or audio URLs.

Instructions

Speech and sound: text-to-speech (default; optional voice_id, see list_resources), sound effects (model 'sfx', optional duration), multi-voice dialogue (model 'dialogue': pass the turns in the dialogue parameter, not prompt), transcription (model 'stt': pass audio_url, get text back; optional diarize/language_code), voice change (model 'voice-changer': audio_url + target voice_id) and audio cleanup (model 'voice-isolation': audio_url). Returns the audio URL (or the transcript for 'stt'). For music, use generate_music.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNoDefault true: wait for the job and return the finished result. Set false to get the task_id back immediately and poll with get_task — use for long jobs (high-quality video, full songs) or when the connection might time out.
modelNoModel, as a short alias or full id. Aliases: 'tts' (default, text-to-speech), 'sfx' (sound effect), 'dialogue', 'stt' (transcribe), 'voice-changer' (transform a voice, needs audio_url), 'voice-isolation' (clean/isolate audio, needs audio_url). Full ids also work. For music use generate_music.
promptNoThe content to synthesize: spoken text for text-to-speech/dialogue, or the sound description for sound effects. Not used for transcription (pass audio_url instead).
diarizeNoTranscription: label who is speaking (speaker diarization). Default false.
dialogueNoModel 'dialogue' only: the conversation as an array of turns, each { text, voice_id } (voice ids from list_resources). Replaces prompt for dialogue.
durationNoDuration in seconds (max 36000 = 10h, a billing ceiling this server imposes — not a model limit). Sound effects: omit for automatic. Transcription: the job is PRICED by this declared length (defaults to 300s = 5 min) — pass the audio's real length or short clips are overcharged.
voice_idNoVoice id for text-to-speech. Discover available voices with the list_resources tool. Falls back to a default voice if omitted.
audio_urlNoSource audio (public https URL) for audio-input models: transcription ('stt'), voice change ('voice-changer'), and cleanup ('voice-isolation'). For local files, upload_file first.
callback_urlNoOptional webhook URL. When set, the tool returns immediately with the task_id and UnificAlly POSTs the result to this URL when the task finishes. Webhook body: { task_id, status: 'completed'|'failed', data: { video_url | image_url | audio_url | ... }, error_message? } — note the media arrives under 'data', not 'output'. Use for long jobs instead of waiting.
confirm_costNoOnly relevant if the operator enabled a spend guard. When a call exceeds the configured confirm threshold it returns a quote; retry with confirm_cost: true to proceed. Safe to ignore otherwise.
language_codeNoTranscription: optional ISO 639 language code (e.g. 'eng', 'spa'). Auto-detected when omitted.
provider_optionsNoEscape hatch for model-specific fields not exposed as named parameters (e.g. Kling multi_shots, Flux steps). Merged into the API 'input' payload. Rejected: fields the tool already manages (prompt, media URLs, task_id, ...) and reserved routing/billing/auth keys (model, callback_url, dry_run, api_key, authorization) — switch models with the 'model' parameter, not here. See https://docs.unifically.com for per-model fields.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description adds the return contract ('Returns the audio URL (or the transcript for \'stt\')') plus mode-specific input requirements. It does not itself mention credit spend, the confirm_cost quote flow, or async polling — those live only in the schema — so it adds value without fully covering the cost side of a billing-affecting tool.

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-loads the general purpose, then walks the modes in a tight parallel construction, and closes with the return value and the music alternative. The single dense paragraph is efficient though it becomes slightly hard to scan at six modes; no sentence is wasted.

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

Completeness4/5

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

For a 12-parameter, nested-object, no-output-schema tool, the description covers mode routing, required inputs per mode, and the return value. The gaps (async/callback behavior, cost confirmation) are documented in the schema rather than the description, so an agent calling this correctly still has what it needs.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3; the description goes further by encoding cross-parameter relationships — dialogue turns go in 'dialogue' rather than 'prompt', stt/voice-changer/voice-isolation take 'audio_url', tts takes 'voice_id' from list_resources. That mode-to-parameter mapping is genuinely useful disambiguation beyond a flat field list.

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?

Opens with a concrete verb+resource ('Speech and sound') and then enumerates the six distinct operations (tts, sfx, dialogue, stt, voice-changer, voice-isolation) with the model alias that selects each. It explicitly separates itself from generate_music, so an agent can route without opening the schema.

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?

Gives per-mode selection guidance ('model \'sfx\'', 'model \'dialogue\'', etc.) and names the sibling alternative with a condition ('For music, use generate_music'). It does not state exclusions for the neighbouring media tools (generate_video/image) or for when to prefer upload_file flows, so it stops just short of full when/when-not coverage.

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

Deploy Server

Other Tools