Skip to content

REST API

Use any ASR backend via HTTP API (local or cloud).

Sign up at dashboard.cohere.com — Canadian-hosted, same as local Apache 2.0 model.

  • Cohere Transcribe — #1 Open ASR Leaderboard, 5.42 avg WER, 14 languages

Note: Cohere’s API requires a language parameter. Set "language": "en" (or your language code) in your config alongside the backend selection.

Bring an API key from OpenAI, and choose from:

  • GPT-4o Transcribe - Latest model with best accuracy
  • GPT-4o Mini Transcribe - Faster, lighter model
  • GPT-4o Mini Transcribe (2025-12-15) - Updated version of the faster, lighter transcription model
  • GPT Audio Mini (2025-12-15) - General purpose audio model
  • Whisper 1 - Legacy Whisper model

Bring an API key from ElevenLabs, and choose:

  • Scribe v2 - Batch transcription, 90+ languages

Shares its key with Scribe v2 Realtime. language and secondary_language work as usual.

Bias toward your vocabulary with keyterms:

{
"rest_body": {
"model_id": "scribe_v2",
"keyterms": ["hyprwhspr", "Hyprland", "Claude Code", "useEffect"]
}
}

Keyterms cost 20% more, and past 100 every request bills as at least 20s. Each stays under 50 characters and 5 words (limits).

Bring an API key from AssemblyAI, and choose:

  • Dictation - Removes filler words and fixes punctuation and self-corrections. Supports 32 languages.

language is sent as language_codes. Options from the Dictation API go in rest_body, sent as one JSON config part:

{
"rest_body": {
"keyterms_prompt": ["hyprwhspr", "Hyprland", "Claude Code"],
"rewrite_mode": "smart"
}
}

If the cleanup fails, you get the plain transcript instead.

Bring an API key from Groq, and choose from:

  • Whisper Large V3 - High accuracy processing
  • Whisper Large V3 Turbo - Fastest transcription speed

Bring an API key from Regolo, European-hosted with zero data retention (GDPR):

  • Faster Whisper Large V3 - High accuracy, zero data retention (GDPR)

Connect to any backend, local or cloud, via your own custom configuration:

{
"transcription_backend": "rest-api",
"rest_endpoint_url": "https://your-server.example.com/transcribe",
"rest_fallback_endpoint_urls": [ // optional ordered fallback endpoints
"https://fallback.example.com/v1/audio/transcriptions"
],
"rest_headers": { // optional arbitrary headers
"authorization": "Bearer your-api-key-here"
},
"rest_body": { // optional body fields merged with defaults
"model": "custom-model",
"keywords": ["one", "two"] // arrays are sent as repeated form fields
},
"rest_api_key": "your-api-key-here", // equivalent to rest_headers: { authorization: Bearer your-api-key-here }
"rest_timeout": 30 // optional, default: 30; per endpoint
}

Audio is sent as 16-bit WAV.

rest_fallback_endpoint_urls are mirrors of the primary, tried in order. They get the same key, headers and body. Failover happens only when an endpoint can’t be reached or answers 429 or 5xx. Behind a keyed https:// primary, http:// fallbacks are skipped.