Speech to text API

Live

Turn audio and video into text in many languages, priced per minute.

From $0.00026 per minute (billed per started minute) across 6 modelsCheapestNemotron 3.5 ASR

from $0.00026/min

Input

Audio or videoaudio_urlA public https link to the audio or video file.

3f563c93-04da-490f-b9ff-023ea49e3893_example.mp3Reading the file's length…

This model detects the spoken language itself.

$0.00026 per minute of audio, billed per started minute.

Example

Example outputMade with these inputs

The sun rose slowly over the quiet valley, painting the hills in soft shades of gold. Below, a river carried the morning light toward the sea, calm and unhurried.

Language: en

Compare Speech to text API models

Every model behind this endpoint, with live prices. Try one in the playground or open its page.

Nemotron 3.5 ASRNVIDIA$0.00026 per minute (billed per started minute)
Cheapest
Page
Whisper Large v3 TurboOpenAI$0.00026 per minute (billed per started minute)
$0.006 per minute (billed per started minute)-95%
Page
Qwen3-ASR 0.6BAlibaba (Qwen)$0.00026 per minute (billed per started minute)
$0.0021 per minute (billed per started minute)-87%
Page
Whisper Large v3OpenAI$0.000585 per minute (billed per started minute)
$0.006 per minute (billed per started minute)-90%
Page
Qwen3-ASR 1.7BAlibaba (Qwen)$0.000585 per minute (billed per started minute)
$0.0021 per minute (billed per started minute)-72%
Page
Voxtral Small 24BMistral AI$0.0039 per minute (billed per started minute)
Below the maker's price
Page

Every model of this tool with its price
		Official			Lengths / sizes	Badges	Actions
Nemotron 3.5 ASRNVIDIA	$0.00026 per minute (billed per started minute)	No official price	—	—	30 min	Cheapest	Page
Whisper Large v3 TurboOpenAI	$0.00026 per minute (billed per started minute)	$0.006 per minute (billed per started minute)	-95%	—	30 min		Page
Qwen3-ASR 0.6BAlibaba (Qwen)	$0.00026 per minute (billed per started minute)	$0.0021 per minute (billed per started minute)	-87%	—	30 min		Page
Whisper Large v3OpenAI	$0.000585 per minute (billed per started minute)	$0.006 per minute (billed per started minute)	-90%	—	30 min		Page
Qwen3-ASR 1.7BAlibaba (Qwen)	$0.000585 per minute (billed per started minute)	$0.0021 per minute (billed per started minute)	-72%	—	30 min		Page
Voxtral Small 24BMistral AI	$0.0039 per minute (billed per started minute)	Below the maker's price	—	—	30 min		Page

Call Speech to text API from your code

One endpoint for every model above. Change the model field to switch.

POSThttps://api.opennan.com/v1/audio/transcriptions

GET/v1/models?category=voiceEvery model of this endpoint, with prices

Get an API key
Create a key in the console. It uses the same balance as the playground.
Create a key

Send your first request

The same request the playground sends. Set OPENNAN_KEY to your key.

curl https://api.opennan.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $OPENNAN_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nemotron-asr","audio_url":"https://cdn.opennan.com/examples/audio/3f563c93-04da-490f-b9ff-023ea49e3893_example.mp3"}'

# Then poll until "status" is "succeeded" or "failed":
curl https://api.opennan.com/v1/tasks/<task id> -H "Authorization: Bearer $OPENNAN_KEY"

Poll the task
The call answers right away with a task id. Ask for the task until it finishes:
GEThttps://api.opennan.com/v1/tasks/{id}
queued
Waiting for a worker
running
Being made
succeeded
Done: outputs[].url holds the files
failed
Failed: you are not charged

Parameters

Built from the live catalog: every value listed here is one the API accepts.

Parameters
Name	Type	Allowed values	Default	Effect on price
`model`requiredWhich model runs the call.	string	whisper-large-v3-turbo · whisper-large-v3 · qwen3-asr-0.6b · qwen3-asr-1.7b · voxtral-small · nemotron-asr	—	—
`audio_url`requiredThe audio or video to transcribe (https link).	URL	—	—	Billed per started minute
`language`optionalThe spoken language as a 2- or 3-letter code (en, th, ja). Leave it out to detect it.	string	—	—	—

Errors and how to fix them

401Missing or wrong key
Send the header Authorization: Bearer with a key from the console.
402Balance too low
Add credit in Billing, then send the same call again.
400A value is not accepted
Read error.message: it names the field. Use a value from the parameter table.
429Too many requests
Wait a few seconds and try again, waiting longer after each 429.

Add Opennan to your AI app

One install gives your AI every Opennan tool: video, images, chat, voice, music, sound effects, 3D, captions and dubbing. Pick your app and follow the steps.

MCP serverhttps://api.opennan.com/v1/mcp

Works in the Codex CLI, the Codex app and the Codex IDE extension: they share ~/.codex/config.toml. If the app or IDE does not see OPENNAN_KEY, use the config.toml option with your key in it. Codex asks before each tool call: approve it to go on.

Get an API key
Create a key in the console. It starts with sk- and uses the same balance as the website.
Create a key

Save your key as OPENNAN_KEY

# macOS / Linux (zsh shown; bash: ~/.bashrc)
echo 'export OPENNAN_KEY="sk-..."' >> ~/.zshrc
source ~/.zshrc

# Windows (PowerShell), then open a new terminal
setx OPENNAN_KEY "sk-..."

3
Install the Opennan plugin: the server plus a skill that teaches your AI to pick models, confirm prices and wait for results
```
codex plugin marketplace add Opennan/opennan-ai-plugin
codex plugin add opennan@opennan
```

Or add only the server

codex mcp add opennan --url https://api.opennan.com/v1/mcp --bearer-token-env-var OPENNAN_KEY

Or add this to ~/.codex/config.toml

[mcp_servers.opennan]
url = "https://api.opennan.com/v1/mcp"
http_headers = { Authorization = "Bearer sk-..." }

4
Check that opennan is listed
```
codex mcp list
```
Restart Codex, then ask for anything
“Make a 5 second video of rain on a neon street, a song to go with it and a poster image.”

Replace sk-... with your own key and keep it private: anyone who has it can spend your balance. Your app can list the tools before you add a key; making anything needs one.

This tool from your AI

Once Opennan is added, your AI calls this tool with arguments like these.

Tool: transcribe_audio
Example arguments: { "model": "nemotron-asr", "audio_url": "https://example.com/speech.mp3" }

Speech to text API: questions

Every model and price

How much does Speech to text API cost?

From $0.00026 per minute (billed per started minute) with Whisper Large v3 Turbo, the cheapest of 6 models here. You see the price before you run.

How do I call it from my code?

Send POST https://api.opennan.com/v1/audio/transcriptions with your API key. It answers with a task id: ask https://api.opennan.com/v1/tasks/{id} until the task succeeds or fails.

Can I switch models without changing my code?

Yes. Change the model field and keep the rest of the request, the same key and the same balance.

Can my AI agent use it?

Yes. Add the MCP server https://api.opennan.com/v1/mcp and call the transcribe_audio tool, or point your agent at https://api.opennan.com/llms.txt.

What happens if a run fails?

A failed run is not charged. You pay only for results.