Voice MCP
Voice MCP is an x402 pay-per-call text-to-speech MCP server for generating WAV/audio speech with standard, controlled, persona, OpenAI-compatible, and batch requests.
List the free voice catalog: 20 voices, 10 personas, 31 languages, pricing buckets, limits, and controls.
Generate low-cost standard-voice speech from text using M1-M5 or F1-F5, with optional language.
Generate controlled speech with granular speed
0.7-2.0and quality steps1-100.Generate expressive persona speech using voices like Storyteller, Narrator, Announcer, Assistant, Urgent, Sage, Spark, Anchor, Velvet, and Echo.
Generate OpenAI-shaped speech requests with
input,voice, optionalmodel, andresponse_format(wav,flac,ogg).Generate batch audio for up to 20 text items in one paid call, with optional default voice/language and total text limit.
Validate voices, languages, formats, ranges, batch size, and character limits locally before paid x402 USDC calls on Base.
Return
audio_base64audio output for MCP clients to store, play, or forward.
Provides tools for generating speech using an OpenAI-compatible API, enabling text-to-speech with multiple voices, personas, languages, speed, quality controls, and batch generation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Voice MCP speak 'Hello, how are you?' in F1 voice"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Voice MCP
Give Your Agent A Voice: x402 pay-per-call speech with 20 voices, 10 personas, 31 languages, granular speed and quality controls, OpenAI-shaped requests, and batch audio.
This MCP wraps https://voice.forgemesh.io, an x402 Voice API with standard voices, persona voices, OpenAI-shaped speech requests, 31 languages, speed controls, quality controls, and batch generation. Payments are made per call in USDC on Base.
Voice Coverage
10 standard voices:
M1-M5,F1-F510 persona voices:
Storyteller,Narrator,Announcer,Assistant,Urgent,Sage,Spark,Anchor,Velvet,Echo31 languages:
en,ko,ja,ar,bg,cs,da,de,el,es,et,fi,fr,hi,hr,hu,id,it,lt,lv,nl,pl,pt,ro,ru,sk,sl,sv,tr,uk,viGranular control: speed
0.7x-2.0x, quality steps1-100, persona selection, OpenAI-shaped audio format requests, and batch generation for up to 20 textsVoice samples are generated on demand by the paid speech tools and returned as
audio_base64WAV output
Related MCP server: forgemesh-imagegen
Voice Samples
Tools
Tool | Price | Purpose |
| Free | Voices, personas, languages, pricing, buckets, and controls |
| $0.005 | Low-cost speech with 10 standard voices |
| $0.005 / $0.006 | Speech with granular speed and quality controls |
| $0.005 / $0.01 | Storyteller, Velvet, Narrator, Announcer, Assistant, Urgent, and more |
| $0.005 | OpenAI-shaped |
| $0.005 | Up to 20 texts per call |
Short prices apply to 1-500 characters. Long prices apply to 501-2000 characters.
The MCP validates voice names, language codes, audio formats, speed/quality ranges, batch item count, and character limits locally before making a paid x402 call.
Install
npm install -g @forgemeshlabs/voice-mcpDocker
Build:
docker build -t voice-mcp .Run over stdio:
docker run --rm -i \
-e WALLET_PRIVATE_KEY=0x... \
voice-mcpCMD arguments:
["node", "index.js"]MCP Config
{
"mcpServers": {
"voice": {
"command": "voice-mcp",
"env": {
"WALLET_PRIVATE_KEY": "0x..."
}
}
}
}Requirements and safety
Use a dedicated, low-balance wallet; the server signs payments with
WALLET_PRIVATE_KEY.The server refuses to sign for any payee other than the ForgeMesh Voice wallet, any network other than Base mainnet, any asset other than USDC, or any amount over the built-in per-call cap ($0.01).
Optional env
X402_MAX_PRICE_USD(per call) andX402_SESSION_BUDGET_USD(cumulative per process, default $10) can only LOWER the built-in caps.The backend URL is fixed to
https://voice.forgemesh.io; all requests are same-origin, time-limited (60s), size-capped (2 MB) and never follow redirects.
Notes
Paid tools require a Base wallet private key with USDC.
The server returns
audio_base64for audio tools so MCP clients can store, play, or forward the WAV bytes.No API keys or subscriptions are required for the voice service itself.
Available Tools
6 toolsgenerate_batch_voicesGenerate Batch VoicesA
Generate WAV audio for up to 20 text items in one paid call using standard voices. Best for queues, notifications, scripted sequences, content batches, and multi-step agent workflows. Costs $0.002 for up to 500 total chars or $0.005 for 501-2000 total chars.
Inputs: items (required), defaults.
generate_controlled_voiceGenerate Controlled VoiceA
Generate WAV speech with granular controls for speed and quality. Use this when an agent needs faster, slower, clearer, more polished, or more deliberate delivery. Costs $0.003 for 1-500 chars or $0.006 for 501-2000 chars.
Inputs: text (required), lang, speed, steps, +1 more.
generate_openai_compatible_voiceGenerate OpenAI-Compatible VoiceA
Generate speech using an OpenAI-shaped request with input, voice, model, and response_format fields. Use this for agents or apps already designed around /v1/audio/speech style payloads. Costs $0.001 for 1-500 chars or $0.003 for 501-2000 chars.
Inputs: input (required), model, voice, response_format.
generate_persona_voiceGenerate Persona VoiceA
Generate expressive WAV speech with persona voices such as Storyteller, Narrator, Announcer, Assistant, Urgent, Sage, Spark, Anchor, Velvet, or Echo. Best for branded agents, characters, demos, stories, alerts, and premium user experiences. Costs $0.005 for 1-500 chars or $0.01 for 501-2000 chars.
Inputs: text (required), lang, speed, steps, +1 more.
generate_standard_voiceGenerate Standard VoiceA
Generate low-cost WAV speech from text using one of 10 standard voices across 31 languages. Best for simple agent narration, status updates, alerts, and short spoken responses. Costs $0.001 for 1-500 chars or $0.003 for 501-2000 chars.
Inputs: text (required), lang, voice.
list_voice_catalogList Voice CatalogA
Free discovery tool. Lists all 20 voices, 10 persona voices, 31 language codes, price buckets, character limits, and granular speed/quality controls before a paid voice generation call.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 6 tools
Each generate tool targets a distinct use case (batch, controlled, OpenAI-compatible, persona, standard), and list_voice_catalog is clearly separate as a discovery tool. No overlapping purposes.
All tools follow a clear verb_noun pattern: generate_* for voice generation and list_voice_catalog for listing. The verbs are appropriate and the pattern is consistent.
Six tools cover the core functionality of a TTS server well. The count is not excessive and each tool has a clear role, making the set scoped and manageable.
The set covers all major text-to-speech workflows: standard, controlled, persona, batch, API-compatible generation, plus catalog discovery. No obvious gaps for the intended domain.
Maintenance
Related MCP Connectors
AI Voice Production Agent: picks from 30+ TTS models, fixes pronunciation, validates every line.
Text to natural speech as MP3: 38 voices, 7 languages, 1,000 chars per call. Paid per call, x402.
Give any AI agent a phone: make and answer calls, get through phone menus, and send texts.
x402 pay-per-call agent tools: token safety/honeypot check, speech to text, TTS, translate, OCR, web
Related MCP Servers
- AlicenseAqualityBmaintenanceProvides high-quality text-to-speech synthesis with 10 natural voices, emotion control, and dynamic pacing for professional applications requiring expressive speech output.52MIT

forgemesh-imagegenofficial
AlicenseAqualityBmaintenanceMCP server for AI image generation with automatic USDC payments on Base mainnet. Generate, remove backgrounds, and upscale images via simple tool calls.4897 npm1MIT- AlicenseNot gradedqualityDmaintenanceEnables AI agents to generate high-quality speech with 54+ voices in multiple languages via MCP tools.21Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to synthesize speech via the unlimitedtts API, handling x402 micropayments, spend policy enforcement, and storage of private MP3 results.MIT