# Voicedex

> Voicedex is a free MCP server for ai models and llm tooling. MCP server to search, compare and price speech-to-text and text-to-speech models. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API, CLI, Web
- **Website:** https://voicedex.dev/mcp
- **Repository:** https://github.com/chandradot99/voicedex
- **MCP Registry name:** io.github.chandradot99/voicedex
- **Categories:** [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-19

## About

The README says Voicedex is an open catalog of speech AI covering 800+ speech-to-text, text-to-speech and speech-to-speech models and 15,000+ stock voices from 120+ providers. This MCP server exposes that catalog to AI assistants, so a client can look up supported languages, features, regions and pricing without leaving the chat.

The server offers seven tools: searching models, fetching a single model record, comparing up to six models, estimating cost for a workload, finding replacements for a model that is being shut down, searching voices, and listing providers and recent catalog changes. Prices are normalised to USD per 1M characters for text-to-speech and USD per hour of audio for speech-to-text, and each result links back to its price source.

It suits developers choosing a speech API, product teams tracking provider price changes or deprecations, and anyone building voice features who wants an assistant to answer catalog questions. The server is streamable HTTP, needs no API key and is read-only; the same data is also available through a free REST API and as a JSON download.

## Features

- **Model search and comparison:** Filters models by type, language, features and region, and compares up to six side by side.
- **Cost estimation:** Calculates USD cost for a given workload, including voice-agent pipelines, on the server side.
- **Shutdown alternatives:** Suggests active replacement models of the same type when a model is being retired.
- **Voice search:** Searches stock voices across providers by language, gender, category and other attributes.
- **Catalog change feed:** Lists recent price changes, deprecations, shutdown notices and newly added models.
- **Source-linked results:** Each result carries its price source, check dates and a link back to the catalog entry.

## Good for

- Finding the cheapest speech-to-text API that supports a given language
- Comparing streaming and pre-recorded pricing across providers before choosing one
- Estimating monthly speech API costs for a planned workload
- Spotting speech models scheduled for shutdown before they break an app
- Locating stock voices by language and gender for a voice product

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http voicedex https://voicedex.dev/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://voicedex.dev/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "voicedex": {
      "url": "https://voicedex.dev/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "voicedex": {
      "type": "http",
      "url": "https://voicedex.dev/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "voicedex": {
      "serverUrl": "https://voicedex.dev/mcp"
    }
  }
}
```

### Grok Bot (Grok Bot desktop app → Connect apps → Add a custom connector)

```sh
https://voicedex.dev/mcp
```

Enter a Name (for example "Voicedex"), choose Type: Remote HTTPS, paste this as the Server URL and choose Add plugin.

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "voicedex": {
      "type": "http",
      "url": "https://voicedex.dev/mcp"
    }
  }
}
```

## Tools

All 8 tools say they're read-only. From the server's own tool annotations; not verified by us.

- `search_models` (says read-only): Search active speech models. Filters combine (AND). Paged: pass next_offset to get more. language: BCP-47 code, e.g. "hi" or "en-GB". Only models that explicitly list it are returned, unless include_unlisted_languages=true also adds models that claim "many languages" without listing them. capability: one feature term, e.g. "speaker_diarization", "voice_cloning", "word_timestamps", "ssml". max_pric
- `get_model` (says read-only): One model's record: pricing with all variants (e.g. streaming vs pre-recorded) and source, languages, capabilities with notes (e.g. "pre-recorded only, English only"), regions, interfaces, audio formats, limits, lifecycle, shutdown date and replacement, open-weights licence, provenance. model: key or loose name. detail="compact" (default) groups regional language codes and trims source URLs; "full
- `compare_models` (says read-only): Compare up to 6 models side by side. Each item can be an exact key "provider/type/model_id" (from search_models) or a loose name like "deepgram nova-3" or "Cartesia Sonic 3". A loose name resolves to the best match and says so in matched_as (with other_candidates): tell the user what was assumed. Unmatched items come back with "did you mean" suggestions when something is close.
- `estimate_cost` (says read-only): Cost in USD for a workload, computed here so no unit conversion is left to the model. models: keys or loose names (up to 6). characters: text to synthesize (TTS). audio_minutes: audio to transcribe (STT/STS), or for TTS the minutes of speech to produce (converted with tts_chars_per_minute, default 900 chars ≈ 150 words/min). Passing an STT and a TTS model with audio_minutes gives a voice-agent pip
- `find_alternatives` (says read-only): Replacements for a model (e.g. one that is shutting down): active models of the same type, ranked by how many of its explicitly listed languages they cover, then shared features, then how close the price is. The provider's own announced successor, if any, comes first. model: key or loose name.
- `search_voices` (says read-only): Search stock voices (15,000+, so results are compact and paged: pass next_offset for more). model: a model id of that provider (voices compatible with it). has_sample=true returns only voices with an audio preview URL.
- `list_providers` (says read-only): Providers in the catalog with model and voice counts, headquarters and access model. Retired providers (shut down or no longer sold) are included only when include_retired=true, with their retirement date.
- `recent_changes` (says read-only): Latest catalog changes, newest first: price changes, shutdown announcements, deprecations, models added. kind: one of price_changed, price_published, shutdown_announced, model_deprecated, model_removed, now_ga, model_added, provider_added, provider_retired.

## FAQ

### Does the MCP server require an API key?

No. The server is free, read-only and needs no key, according to its page and README.

### Which transport does it use?

It uses Streamable HTTP at https://voicedex.dev/mcp.

### Which AI clients are supported?

The site gives setup steps for Claude web and desktop, Claude Code, Cursor and VS Code, and says any MCP client can connect.

### How are prices normalised?

The README says text-to-speech is normalised to USD per 1M characters and speech-to-text to USD per hour of audio, with prices taken only from vendor pages.

### Is Voicedex free?

Yes. Voicedex is free to use.

### How do I add Voicedex to Claude Code?

Run this command in your terminal: claude mcp add --transport http voicedex https://voicedex.dev/mcp

### What are the best alternatives to Voicedex?

The closest alternatives to Voicedex are MCP, Voxtral TTS MCP, Agent Data Tools: Speech to text and text to speech, AI API Prices and Texttospeech Mcp.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Status and tools: checked automatically by AIPoweredBot on 19 November 2026.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [MCP](https://ai-powered.com/mcp/mcp-mwi57hue): MCP is a paid MCP server for design and media.
- [Voxtral TTS MCP](https://ai-powered.com/mcp/voxtral-tts-mcp): Voxtral TTS MCP is an open-source MCP server for design and media.
- [Agent Data Tools: Speech to text and text to speech](https://ai-powered.com/mcp/agent-data-tools-speech-to-text-and-text-to-speech): Agent Data Tools: Speech to text and text to speech is a paid MCP server for design and media.
- [AI API Prices](https://ai-powered.com/mcp/ai-api-prices): AI API Prices is an open-source MCP server for design and media.
- [Texttospeech Mcp](https://ai-powered.com/mcp/texttospeech-mcp): Texttospeech Mcp is a freemium MCP server for ai models and llm tooling.
- [Speechtotext Mcp](https://ai-powered.com/mcp/speechtotext-mcp): Speechtotext Mcp is a freemium MCP server for ai models and llm tooling.
- [Modelglass](https://ai-powered.com/mcp/modelglass): Modelglass is a freemium MCP server for ai models and llm tooling.
- [deAPI MCP Server](https://ai-powered.com/mcp/deapi-mcp-server): deAPI MCP Server is an MCP server for design and media.

---
Source: https://ai-powered.com/mcp/voicedex
