Transcription Models
Skribby uses a unified naming convention for all supported transcription models to make it easier to understand which provider and model you are using. This guide explains how to format your transcription model keys, understand aliases, and what to expect in API responses.
Standardized Naming Convention
Skribby uses the format <provider>/<model> for all official transcription model keys.
When specifying a transcription_model in the API, we highly recommend using the official key for all new integrations:
{
"transcription_model": "deepgram/nova-2-realtime",
"meeting_url": "...",
"service": "gmeet",
"bot_name": "My Meeting Bot"
}
Supported Models & Aliases
We maintain backwards compatibility with older, simpler naming conventions (like whisper or deepgram). These are called aliases. When you request an alias, Skribby internally maps it to the corresponding official key.
Below is the full mapping of official keys to their supported aliases:
| Official Key | Supported Aliases | Type |
|---|---|---|
none | none | No Transcription |
openai/whisper-large-v3 | whisper | Standard |
soniox/stt-async-v4 | soniox, soniox/latest | Standard |
soniox/stt-rt-v4 | soniox-realtime, soniox/latest-realtime | Realtime |
assemblyai/universal-2 | assembly-ai | Standard |
assemblyai/universal-streaming | assembly-ai-realtime | Realtime |
deepgram/nova-2 | deepgram | Standard |
deepgram/nova-2-realtime | deepgram-realtime | Realtime |
deepgram/nova-3-multilingual | deepgram-v3 | Standard |
deepgram/nova-3-multilingual-realtime | deepgram-realtime-v3 | Realtime |
speechmatics/batch-standard | speechmatics | Standard |
speechmatics/realtime-standard | speechmatics-realtime | Realtime |
revai/reverb-foreign-language | rev-ai | Standard |
elevenlabs/scribe-v1 | elevenlabs | Standard |
elevenlabs/scribe-v2 | elevenlabs-v2 | Standard |
elevenlabs/scribe-v2-realtime | elevenlabs-realtime-v2 | Realtime |
gladia/async | gladia | Standard |
gladia/realtime | gladia-realtime | Realtime |
salad/transcription | salad | Standard |
API Responses
When you create a bot or recording, the Skribby API response includes two fields relating to your model selection:
transcription_model: This field echoes the exact string you provided in the request. If you sent an alias, this field will show the alias.transcription_model_key: This field always returns the canonical, official key that Skribby actually used to run the transcription.
This design ensures that your application won't break if it expects transcription_model to match your request, while still giving you visibility into the exact provider and model version being used under the hood.
Example 1: Request with Official Key
Request
{
"transcription_model": "deepgram/nova-2"
// ...
}
Response
{
"transcription_model": "deepgram/nova-2",
"transcription_model_key": "deepgram/nova-2"
// ...
}
Example 2: Request with Legacy Alias
Request
{
"transcription_model": "whisper"
// ...
}
Response
{
"transcription_model": "whisper",
"transcription_model_key": "openai/whisper-large-v3"
// ...
}
Example 3: Request with Semantic Alias
Some aliases, like soniox/latest, are designed to always point to a provider's best or most recent model.
Request
{
"transcription_model": "soniox/latest"
// ...
}
Response
{
"transcription_model": "soniox/latest",
"transcription_model_key": "soniox/stt-async-v4"
// ...
}