---
area: "speech"
title: "Speech"
tools: 3
mcp_server: "https://api.conecto.chat/mcp/speech"
auth: "Authorization: Bearer <conecto_sk_ key>"
docs_url: "https://conecto.chat/tools/speech"
---

# Speech

Speech to text and text to speech. Recordings from the file store become text in about 100 languages, with who spoke when, and text is read aloud as an MP3 in a stock voice.

Replaces: Otter.ai, Rev, Speechify.

## MCP server

`https://api.conecto.chat/mcp/speech` connects the Speech tools only, plus the account tools that come with every MCP server. It speaks MCP over Streamable HTTP; send the key as `Authorization: Bearer <conecto_sk_ key>`. Every tool here is also a REST call: `POST https://api.conecto.chat/v1/tools/<name>` with the arguments as a JSON object.

## ChatGPT and Claude

Add `https://api.conecto.chat/v1/mcp` as a connector in ChatGPT or Claude, one for every area, and tick Speech when you sign in. It signs in with OAuth: someone on the account signs in on conecto.chat, ticks the areas it may use and allows it, and it runs on a key of its own that the owner can revoke.

## OpenAPI

For a custom GPT's Actions: `https://api.conecto.chat/v1/openapi/speech.json` (OpenAPI 3.0, the key as a Bearer token). For Power Automate, Logic Apps and Copilot Studio connectors: `https://api.conecto.chat/v1/openapi/speech.swagger.json` (OpenAPI 2.0, the key in the X-Api-Key header). Both list this area's tools and the account tools.

Prices: Transcribing $0.01 per started minute of audio · reading text aloud $0.07 per 1,000 characters, rounded up, up to $0.35 · voices free. A call that fails costs nothing.

## Tools

| Tool | What it does | Price |
|---|---|---|
| [speech_transcribe](https://conecto.chat/tools/speech/speech_transcribe.md) | Turns the speech in an audio or video file from the store into text, in about 100 languages, with speakers and timestamps if asked. | $0.01 per started minute of audio. |
| [speech_synthesize](https://conecto.chat/tools/speech/speech_synthesize.md) | Reads text aloud in a stock voice and saves the MP3 in the file store with a download link; up to 5,000 characters a call. | $0.07 per 1,000 characters, rounded up, up to $0.35. |
| [speech_list_voices](https://conecto.chat/tools/speech/speech_list_voices.md) | The stock voices text can be read aloud in; each speaks about 30 languages, and the text decides which. | Free up to 1,000,000 reads a month. |

## Example jobs

- Transcribe a supplier's voicemail and add what they said to their CRM record.
- Turn a recorded bike fitting into notes of who said what.
- Record the phone line's holiday greeting as an MP3.