apps/web/content/docs/pro/1.better-transcription.mdx
Pro includes access to premium cloud transcription services that offer higher accuracy than local models, especially for accented speech, technical jargon, and noisy environments.
Pro subscribers get access to curated cloud transcription models that work out of the box with no configuration required. These models are selected for quality and reliability, and API keys are managed automatically.
When you use Pro's curated transcription, you don't pick a specific provider — Char's server automatically selects the best one based on your configured languages. The routing logic evaluates each provider's language support quality and picks the highest-quality match.
Provider priority order:
| Priority | Provider | Default Model | Best For |
|---|---|---|---|
| 1 | Deepgram | nova-3 | English, general use |
| 2 | Soniox | stt-rt-v4 | Multilingual (e.g., Korean + English) |
| 3 | AssemblyAI | universal | Speaker diarization |
| 4 | Gladia | solaria-1 | Code switching |
| 5 | ElevenLabs | scribe_v2_realtime | Real-time quality |
| 6 | Fireworks | whisper-v3-turbo | Whisper-based |
| 7 | OpenAI | gpt-4o-transcribe | Final fallback |
For example, when transcribing Korean + English, Soniox is selected over Deepgram because it has better multilingual support — even though Deepgram has higher base priority. The router sorts by language quality first, then falls back to priority order:
<GithubCode url="https://github.com/fastrepl/char/blob/main/crates/transcribe-proxy/src/hyprnote_routing.rs#L70-L111" />If you want to use a specific transcription provider, you can bring your own API key. Supported providers include:
| Provider | Best For | Languages |
|---|---|---|
| Deepgram | Real-time accuracy, keyword handling | 30+ |
| AssemblyAI | Speaker diarization, streaming | 20+ |
| Gladia | Code switching, multi-channel audio | 90+ |
| OpenAI | Batch transcription, Whisper API | 50+ |
| Soniox | High accuracy, enterprise features (v4 and v3 models) | 70+ |
| ElevenLabs | High-quality real-time transcription | 30+ |
| DashScope | Qwen3-ASR real-time speech recognition | 10+ |
| Mistral | Voxtral audio transcription | 10+ |
To use BYOK, go to Settings > Transcription and enter your API key for your preferred provider.
Char checks if your selected provider supports your configured languages. If there's a mismatch, you'll see a warning with suggestions for compatible providers. Configure your languages in Settings > Language & Vocabulary.
When using cloud transcription, your recorded audio is sent to the selected provider for processing:
pro.hyprnote.com and forwarded to a curated STT provider. The proxy does not store your audio.Here is how Char selects the correct adapter for your configured provider — each provider has its own adapter that handles the audio stream:
<GithubCode url="https://github.com/fastrepl/char/blob/main/crates/listener-core/src/actors/listener/adapters.rs#L22-L102" />Sent alongside your audio stream:
<GithubCode url="https://github.com/fastrepl/char/blob/main/crates/listener-core/src/actors/session/supervisor.rs#L122-L134" />NOT sent to the provider:
Your audio files and transcripts are always stored locally on your device regardless of which transcription method you use. Cloud providers only receive the audio stream for processing and return the transcript.
Char logs metadata about each STT session to PostHog for usage tracking. No audio or transcription text is ever logged.
<GithubCode url="https://github.com/fastrepl/char/blob/main/crates/transcribe-proxy/src/analytics.rs#L26-L28" />Logged: provider name, session duration. Not logged: audio content, transcription text, meeting content.
All STT providers used by Pro have zero data retention for real-time/streaming transcription and are SOC 2 compliant.
| Policy | Details |
|---|---|
| Data retention | Zero storage by default — no audio or transcript retained after processing |
| Training | Does not train on customer data (acts as data processor) |
| Compliance | SOC 2 Type 2, GDPR, HIPAA, PCI, CCPA |
| Encryption | TLS 1.2+ (transit), AES-256 (rest) |
| Data location | US (default), EU available (api.eu.deepgram.com) |
"Deepgram's default configuration meets the strictest requirements with zero retention after processing."
Official docs: Privacy Policy · Data Security · Information Security & Privacy
| Policy | Details |
|---|---|
| Data retention | No retention for real-time API |
| Training | Never uses customer audio or transcripts for model training |
| Compliance | SOC 2 Type 2, GDPR, HIPAA |
| Encryption | TLS 1.2+ (transit) |
| Data location | US (default), EU (api.eu.soniox.com), Japan (api.jp.soniox.com) |
"No retention – Soniox does not store your audio or transcript data unless explicitly requested through a service that supports storage."
"No model training – your audio and transcripts are never used to improve Soniox models or services."
Official docs: Privacy Policy · Security & Privacy · Data Residency
| Policy | Details |
|---|---|
| Data retention | Zero for streaming API (when opted out of model training) |
| Training | Optional — can opt out |
| Compliance | SOC 2 Type 2, GDPR, HIPAA, PCI-DSS 4.0 Level 1 |
| Encryption | TLS 1.3 (transit), AES-256 (rest) |
| Data location | US (default), EU (Dublin, Ireland) |
"If you are opted out of model training, we offer zero data retention of audio and transcripts for our Streaming product."
Official docs: Privacy Policy · Security · Trust Center
For the full details on every data flow, see AI Models & Data Privacy.
Use cloud transcription when you need maximum accuracy and have internet access. Use local transcription (Whisper models) when privacy is paramount or you're offline. Local models support 50+ languages and run entirely on your device.
For local STT model details and manual download instructions, see Local Models.