Skip to content

VoiceHue text to speech MCP server

io.github.voicehue/voicehuevoicehuestreamable-httpv1.0.0Scanned

Remote text-to-speech MCP server with text_to_speech and list_voices tools. Free plan.

8 tools: 5 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 5 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 7
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

5 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the VoiceHue text to speech MCP server can do

The VoiceHue text to speech MCP server is published by the GitHub account voicehue. It has 8 tools. It can create or change data (5 tools: voice_studio, text_to_speech, create_speech_job, create_dialogue and 1 more), but cannot delete data. 3 tools only read.

7 tools bring in text other people can write (voice_studio, text_to_speech, list_voices and 4 more); 1 tool can send data out of your system (create_speech_job).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.

Last scanned Nov 18, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

8 tools

Changes things 5Claude Code: ask
  • create_dialogueSpeak a conversation with several voices and get ONE merged audio file (MP3 by default, or WAV).Reads text others writeNo findings

    Why it is in this group

    • The name "create_dialogue" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Speak a conversation with several voices and get ONE merged audio file (MP3 by default, or WAV). Each block has its own voice, text and optional language, speed, pitch, volume and pause after it. Up to 20 blocks on the free plan and 100 on pro, and 3,000 characters across all blocks per call. Each block is charged like a text_to_speech call with its voice. Use list_voices first to get voice ids.

    Annotations the server declares

    • title: Create a multi-voice dialogue
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • create_speech_jobQueue a long text (up to 20,000 characters) for speech.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "create_speech_job" says "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Queue a long text (up to 20,000 characters) for speech. Returns a job id at once; call get_speech_job with it until the status is completed, then download the audio from its link. Use text_to_speech instead for texts up to 3,000 characters. The text is charged once, only when all of it was spoken.

    Annotations the server declares

    • title: Create a long speech job
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • estimateHow many premium characters a text would use with a voice, without making audio.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    How many premium characters a text would use with a voice, without making audio. Standard voices are free; premium voices use at most one premium character per character (value voices less). Give the text, or just its length in characters. Free to call.

    Annotations the server declares

    • title: Estimate premium characters
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • text_to_speechConvert text to spoken audio with a VoiceHue voice.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "convert": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Convert text to spoken audio with a VoiceHue voice. Returns the audio (MP3 by default, or WAV) and a one-line summary with the voice, number of characters and duration. Up to 3,000 characters per call. Use list_voices first to get a valid voice id.

    Annotations the server declares

    • title: Text to speech
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • voice_studioCreate and manage PRIVATE voices.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Create and manage PRIVATE voices. Actions: capabilities, list, quote (for_action design/clone/save/synthesize/delete), design, save, clone, synthesize, delete, operation, rename. Rename changes only the current account’s personal voice display name, takes voice_id and name, costs zero and needs no quote. For generation, always quote first and obtain the user's approval for a nonzero credit cost; then send max_credits and a stable UUID request_id. Design takes a description and 100–1000 character preview text; save selects candidate from its operation_id. Clone takes 3–120s WAV/MP3 base64 (up to 2MB) and consent=true ONLY after the user confirms voice ownership or permission. Synthesize returns a private expiring audio_url. Engine standard is currently free; premium uses account credits. Never retry a mutation with a new request_id after a timeout; read operation status. List includes slot_usage by engine and per-voice available/availability_reason. Expired hosting records can be displayed for management; select only available voices for synthesis. Personal IDs and previews are private to the authenticated account.

    Annotations the server declares

    • title: Voice studio
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • get_speech_jobStatus of a job from create_speech_job: queued, running, completed or failed.Reads text others writeNo findings

    Why it is in this group

    • The name "get_speech_job" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Status of a job from create_speech_job: queued, running, completed or failed. A completed job carries a download link valid for one hour (call again for a new one); the audio is kept for 24 hours.

    Annotations the server declares

    • title: Get a speech job
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_usageWhat this key's account has left: standard characters today and this month (limits, used, remaining, plan, requests per minute), the premium characters left (this month, used today…Reads text others writeNo findings

    Why it is in this group

    • The name "get_usage" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    What this key's account has left: standard characters today and this month (limits, used, remaining, plan, requests per minute), the premium characters left (this month, used today and the daily limit), today's free premium trial, characters that expire soon, and when the daily limits reset (00:00 UTC). Free to call; no audio is made.

    Annotations the server declares

    • title: Get usage and balance
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_voicesList the public VoiceHue voices a key can use: id, name, language, gender and tier.Reads text others writeNo findings

    Why it is in this group

    • The name "list_voices" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    List the public VoiceHue voices a key can use: id, name, language, gender and tier. Standard voices use the key's free plan; premium voices use the account's daily free premium trial, then its premium characters: char_rate is what one character of text uses (1 for most, less for value voices, value_factor says how much further they go). Pass a voice id to text_to_speech.

    Annotations the server declares

    • title: List voices
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write7
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 19, 2026, 17:23 UTC, unchanged since Nov 12, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
5
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://voicehue.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://voicehue.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://voicehue.com/mcp: tools/list returned 8 tools to an anonymous client, including voice_studio (write), text_to_speech (write), create_speech_job (write), create_dialogue (write), estimate (write)

    What this check looks for

Posture changes

  1. Nov 12, 2026
    • Tools that change things, listed without credentials: 1 to 5

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools6 added, 2 changed.+6 added~2 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 5.View diff
    • Tools that change things, listed without credentials: 1 to 5

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http voicehue https://voicehue.com/mcp --header 'Authorization: <your-authorization>'
claude mcp add --transport http voicehue https://voicehue.com/mcp --header 'Authorization: <your-authorization>'

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__voicehue__list_voices",
      "mcp__voicehue__get_speech_job",
      "mcp__voicehue__get_usage"
    ],
    "ask": [
      "mcp__voicehue__voice_studio",
      "mcp__voicehue__text_to_speech",
      "mcp__voicehue__create_speech_job",
      "mcp__voicehue__create_dialogue",
      "mcp__voicehue__estimate"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as voicehue. Review it before you use it.

Capability tags behind 7 rules
  • mcp__voicehue__voice_studio untrusted-input
  • mcp__voicehue__text_to_speech untrusted-input
  • mcp__voicehue__list_voices untrusted-input
  • mcp__voicehue__create_speech_job untrusted-input, outbound
  • mcp__voicehue__get_speech_job untrusted-input
  • mcp__voicehue__create_dialogue untrusted-input
  • mcp__voicehue__get_usage untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.voicehue/voicehue/verify?hash=4316b6b13fa3ed8cd00f9b86a4aee7225eb99b327ec3c0a23a39b1cf14b1b4e2" | jq -e '.changed == false'

Pinned hash 4316b6b13fa3, from Nov 18, 2026, 06:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.voicehue/voicehue/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.voicehue/voicehue
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.voicehue/voicehue.svg)](https://radar.anlyon.com/servers/io.github.voicehue/voicehue)

Source: MCP Registry. Synced Nov 4, 2026, 12:18 UTC.

VoiceHue text to speech MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the VoiceHue text to speech MCP server safe?

No scan can promise that. What its definitions show: 8 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the VoiceHue text to speech MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the VoiceHue text to speech MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the VoiceHue text to speech MCP server have?

8 tools: 5 write, 3 read. voice_studio, text_to_speech, create_speech_job, create_dialogue, estimate, list_voices, get_speech_job and get_usage.

Does the VoiceHue text to speech MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the VoiceHue text to speech MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_speech_job.

Has the VoiceHue text to speech MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.