SpeaklySpeakly

Other Providers

ElevenLabs, Mistral, Deepgram, Google Cloud and custom endpoints

Besides OpenAI and Groq, the Your API Key engine supports ElevenLabs, Mistral, Deepgram, Google Cloud Speech-to-Text and any OpenAI-compatible endpoint of your own.

They are all configured in the same place: Settings → Transcription → engine Your API Key → pick the provider in the Provider row → paste the key → Test Connection. The app's own summary applies to every one of them: the key is encrypted and stored locally, calls go directly from Speakly to the provider rather than through Speakly's servers, the provider bills you for usage, and an internet connection is required.

ElevenLabs

  1. Create a key at elevenlabs.io/app/developers/api-keys
  2. Paste it into ElevenLabs API Key — it starts with sk_
  3. Click Test Connection and wait for "API key is valid"

There is no model dropdown: the provider card is labelled Scribe v1 and the panel states "Model: Scribe v1 - ElevenLabs' speech-to-text model with support for 99 languages, speaker diarization, and audio event detection." ElevenLabs is also the only provider that gives Live Transcription a true realtime stream; every other engine uses the chunked path.

Mistral (Voxtral)

  1. Create a key at console.mistral.ai/api-keys
  2. Paste it into Mistral API Key
  3. Click Test Connection
  4. Pick a model under Model — the list is fetched from your Mistral account once the key is valid; the default is voxtral-mini-latest

Deepgram

  1. Create a key at console.deepgram.com/settings/api-keys
  2. Paste it into Deepgram API Key
  3. Click Test Connection
  4. Pick a model under Model — also fetched from your account; the stored default is nova-2

The panel notes "Free tier includes $200 credit."

Google Cloud Speech-to-Text

AI Studio keys do not work
Speakly says it plainly in the panel: "Google AI Studio keys do NOT work with Speech-to-Text. You need a Google Cloud Console API key." A key created in AI Studio will fail validation.
  1. Open console.cloud.google.com/apis/credentials
  2. Enable the Speech-to-Text API for that project
  3. Create an API key under Credentials — it starts with AIza
  4. Paste it into Google Cloud API Key and click Test Connection
  5. Pick a model under Speech-to-Text Model

Google is the one provider whose model list is curated inside Speakly: Default (Recommended) (selected initially), Latest Short, Latest Long, Command & Search, Phone Call, Video. The two Latest models carry the in-app warning "limited language support (mainly EN, ES, FR, DE, IT, JA, KO, ZH)", so keep Default unless you specifically need a specialised model.

Custom OpenAI-compatible endpoint

The Custom provider points Speakly at any service that implements OpenAI's transcription API — the panel gives the examples: "Connect to any service that implements the OpenAI Whisper API format, such as LocalAI, vLLM, or your own hosted endpoint."

  1. Pick Custom in the Provider row
  2. Base URL: the API root, e.g. https://api.example.com/v1
  3. API Key: the token your endpoint expects
  4. Model Name: the model id to request — whisper-1 by default, "e.g., whisper-1, whisper-large-v3"
  5. Click Test Connection; "Configuration valid" means all three fields are saved
  6. Clear wipes the base URL, key and model name
Other Providers — Speakly