Saidwire Speech-to-Text runs on your own machine — the client starts it, so there is no endpoint to ping. 346 installs a week from pypi. Last commit 1 Nov 2026.
Transcribe local audio files and public audio URLs to text, SRT/VTT or word timestamps.
Today is the operative word: we check Saidwire Speech-to-Text every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add saidwire-mcp -e 'SAIDWIRE_API_KEY=<SAIDWIRE_API_KEY>' -- uvx saidwire-mcp
{
"mcpServers": {
"saidwire-mcp": {
"command": "uvx",
"args": [
"saidwire-mcp"
],
"env": {
"SAIDWIRE_API_KEY": "<SAIDWIRE_API_KEY>"
}
}
}
}
[mcp_servers.saidwire-mcp]
command = "uvx"
args = ["saidwire-mcp"]
env = { SAIDWIRE_API_KEY = "<SAIDWIRE_API_KEY>" }
{
"mcpServers": {
"saidwire-mcp": {
"command": "uvx",
"args": [
"saidwire-mcp"
],
"env": {
"SAIDWIRE_API_KEY": "<SAIDWIRE_API_KEY>"
}
}
}
}
{
"servers": {
"saidwire-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"saidwire-mcp"
],
"env": {
"SAIDWIRE_API_KEY": "<SAIDWIRE_API_KEY>"
}
}
}
}
Put your own value in place of
<SAIDWIRE_API_KEY> (Saidwire API key (free key with 120 hours at https://saidwire.com/dev)).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
SAIDWIRE_MAX_DOWNLOAD_MB (Size limit in MB for transcribe_url downloads (default 100)).
Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.
Instagram Reels to text in bulk: transcripts with timestamps, SRT and VTT for public Reels.
Transcribe local files and URLs with SpeechWeave's OpenAI-compatible Speech-to-Text API.
Pay-per-minute speech-to-text: audio URL to text, SRT or VTT. Paid via x402 or credits.
Audio, video and podcast feeds to text with Whisper. Timestamps, SRT/VTT, 99 languages. Per minute.
Transcribe public audio/video URLs and retrieve transcripts, SRT, and VTT subtitles.
Whisper speech to text for podcast, audio and video URLs, 90+ languages, timestamped output.
Transcribe every audio or video link in a list: plain text, or speakers, timestamps and SRT
Answers built from our own checks of this server.