Speech to text
Transcribe an audio file into text, with the detected language, the total duration and per-segment timings when you ask for them.
What a call costs
Billed on the exact size of your request, minimum $0.0020 per call.
a price before every call. failed calls are never charged.
When to use it
Use when you have a recording and need the words: a voice note, an interview, a podcast, a meeting, a video's audio track. Give a public https link to the file. Billed per second of audio, rounded up, so set max_duration_seconds to roughly how long the recording is and the hold on your wallet matches.
Inputs
Speech to text takes 4 fields, 1 of them required. Anything you leave out falls back to the tool's own default.
| Field | Type | Required | What it does |
|---|---|---|---|
| audio_url | string | yes | Public http or https link to the audio file. Links to private, internal or loopback addresses are refused. Up to 50 MB. |
| language | string | optional | Language hint as an ISO code, e.g. en or fr. Leave it out to let the model detect the language. |
| include_timestamps | boolean | optional | Return per-segment start and end times. Adds latency on clips under 30 seconds. |
| max_duration_seconds | integer | optional | Roughly how long the recording is. This sizes the hold on your wallet; you are billed for the real duration, which is usually less. Audio longer than this is still transcribed but is billed at this ceiling. |
How to call it
Connect once and your agent can reach Speech to text the same way it reaches everything else in the catalog. Add Goro as an MCP connector, or paste the setup line into an agent that reads skills.
MCP
Add this server in Claude, Claude Code, or any MCP client.
https://mcp.usegoro.ai/mcp
Skill
One line in your agent's chat. It sets itself up.
set up https://usegoro.ai/SKILL.mdOr plain HTTP
POST /v1/run
{
"endpoint": "voice.transcribe",
"input": {
"audio_url": "https://example.com/media/team-standup.mp3",
"include_timestamps": false,
"max_duration_seconds": 600
}
}Related tools
More from voice and audio, or browse the full tool catalog.
Clone a voice
Create a reusable voice model from one or more recordings of a person speaking, and get back a voice_id you can pass to voice.speak.
FreeDelete a voice
Permanently delete one of your cloned voices, at the provider as well as here.
FreeList your voices
List the voice models this workspace owns, with the id to pass to voice.speak, when each was created and what consent was attested for it.
FreeText to speech
Turn text into natural speech and get back a link to the audio file.
$0.0450 per 1,000 UTF-8 bytes of text (roughly one minute of speech)Further reading: What is MCP? The Model Context Protocol, explained
Run Speech to text from your agent.
One balance for every tool in the catalog. Start with Build, $25 of credit for $19 a month.
Get started