# Privocio — Private Speech-to-Text API (Full Reference)

> Privacy-first, flat-rate speech-to-text API for AI agents, developers, and teams that need accurate transcription without per-minute billing or data exposure.

Privocio is a hosted and self-hosted speech-to-text (STT) API designed as a drop-in replacement for the OpenAI Whisper API. It provides fixed-price plans billed every 4 weeks, three output modes optimized for different workflows, and a strict privacy-first architecture where audio and transcripts are never used for model training.

**Operated by:** The Useless Company PTE LTD
**Founded:** 2026
**Contact:** hello@privocio.com

---

## Core Value Proposition

- **Privacy-first**: Audio and transcripts are never shared, sold, or used to train models. Self-hosted deployment available for full data sovereignty.
- **Predictable pricing**: Flat-rate plans billed every 4 weeks — no per-minute charges, no overage fees, no surprise bills.
- **OpenAI SDK compatible**: Works as a drop-in replacement for the OpenAI Whisper API. Change `base_url` and you're done.
- **Token optimization**: Agent output mode reduces downstream LLM token usage by approximately 60% by removing filler words, silence markers, and transcript noise before the text reaches your model.
- **Self-hosted option**: Deploy on your own infrastructure for teams with strict compliance, data residency, or air-gapped requirements.

---

## Plans and Pricing

| Plan | Price | Audio Allowance | API Access | Key Limits |
|------|-------|-----------------|------------|------------|
| Free | $0 | 3 hours / 4 weeks | Browser only | 3 RPM, 1 concurrent, 3 min/request, 10 MB uploads |
| Go | $19 / 4 weeks | 400 hours / 4 weeks | API key | 30 RPM, 2 concurrent, 15 min/request, 100 MB uploads |
| Pro | $39 / 4 weeks | 800 hours / 4 weeks | API key | 30 RPM, 2 concurrent, 15 min/request, 100 MB uploads, up to 10 team members |
| Enterprise | Custom | Unlimited | API key + SSO | Custom limits, self-hosted, dedicated support, SLAs, audit logs |

Quarterly billing available: Go $51.30 / 3 months (save 10%), Pro $105.30 / 3 months (save 10%).

No credit card required for the Free plan. No account needed for the browser transcription tool.

---

## Output Modes

Privocio supports three transcription output modes in a single API, selectable per request:

- **Raw**: Full verbatim transcript with all filler words, false starts, and repetitions preserved. Ideal for legal, compliance, and archival use cases where verbatim accuracy is required.
- **Clean**: Noise removed, punctuation corrected, readability improved. Ideal for meeting notes, content creation, and human consumption.
- **Agent**: Structured JSON output with token-efficient formatting optimized for AI agent consumption. Removes transcript noise before it reaches your LLM, reducing context size and downstream token costs by approximately 60%. Includes speaker labels, timestamps, and structured segments.

---

## Technical Specifications

- **API base URL**: `https://api.privocio.com`
- **API version**: `/v1`
- **Authentication**: Bearer token (API key from dashboard, or session token for browser clients)
- **Supported audio formats**: MP3, WAV, M4A, FLAC, OGG, WebM
- **Supported languages**: 100+ with automatic language detection
- **Max audio per request**: 15 minutes (paid plans), 3 minutes (free)
- **Max upload size**: 100 MB (paid plans), 10 MB (free)
- **Response format**: JSON (full text, segments with start/end timestamps, speaker labels)
- **Streaming**: Server-Sent Events (SSE) with real-time segment delivery
- **Speaker diarization**: Automatic speaker separation with configurable speaker count
- **SDK compatibility**: Works with OpenAI Python SDK and OpenAI Node.js SDK (change `base_url`/`baseURL`)
- **Latency**: ~420ms p95 end-to-end for typical audio segments
- **Uptime SLA**: 99.9% target on Go and Pro plans
- **Health endpoints**: `GET https://api.privocio.com/healthz` (liveness), `GET https://api.privocio.com/v1/status` (component health)
- **Webhooks**: Async callback support for batch processing workflows
- **Requests per minute**: 3 (Free), 30 (Go/Pro), Custom (Enterprise)
- **Concurrent requests**: 1 (Free), 2 (Go/Pro), Custom (Enterprise)

---

## Integration Examples

### Python (OpenAI SDK)

```python
from openai import OpenAI

client = OpenAI(
    api_key="your-privocio-api-key",
    base_url="https://api.privocio.com/v1"
)

transcription = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("meeting.mp3", "rb"),
    response_format="json"
)
print(transcription.text)
```

### JavaScript / Node.js (OpenAI SDK)

```javascript
import OpenAI from "openai";
import fs from "fs";

const client = new OpenAI({
  apiKey: "your-privocio-api-key",
  baseURL: "https://api.privocio.com/v1",
});

const transcription = await client.audio.transcriptions.create({
  model: "whisper-1",
  file: fs.createReadStream("meeting.mp3"),
  response_format: "json",
});
console.log(transcription.text);
```

### cURL

```bash
curl https://api.privocio.com/v1/audio/transcriptions \
  -H "Authorization: Bearer your-privocio-api-key" \
  -F model="whisper-1" \
  -F file="@meeting.mp3" \
  -F response_format="json"
```

---

## Privacy Architecture

Privocio is built around a privacy-first architecture with the following guarantees:

- **No model training on customer audio**: Your audio is never used to train or fine-tune shared models.
- **No third-party sub-processors**: Audio is processed in isolation on Privocio infrastructure.
- **Data retention controls**: Customers control how long transcripts and audio are retained.
- **Encryption in transit**: All API traffic uses TLS 1.2+ (HTTPS/WSS).
- **Self-hosted deployment**: Enterprise customers can deploy Privocio on their own infrastructure — on-premise, private cloud, or air-gapped networks. Audio never leaves your perimeter.
- **Data Processing Addendum (DPA)**: Available for enterprise customers requiring GDPR-compliant data processing terms.

---

## Compliance

Privocio supports compliance-sensitive deployments through:

- **HIPAA-aligned architecture**: No data sharing, no third-party training, self-hosted deployment for healthcare organizations. BAA available for enterprise customers — contact hello@privocio.com.
- **GDPR support**: DPA available, EU data residency via self-hosted deployment.
- **SOC 2**: In progress — contact sales for current status.
- **Data sovereignty**: Deploy in any cloud region or on-premise to meet data residency requirements.

---

## Use Cases

### AI Agents
Voice commands from users are transcribed to structured JSON via Agent mode, then passed to agent frameworks such as LangChain, CrewAI, or AutoGen. The ~60% token reduction means lower LLM costs per agent turn. Speaker diarization and timestamps are included in the structured output.

### Healthcare
Healthcare organizations use Privocio for clinical note dictation, telemedicine transcription, medical dictation (radiology, pathology), and patient intake. Self-hosted deployment keeps patient audio within the organization's network perimeter. HIPAA-aligned architecture with no third-party data access.

### Finance
Trading floors, client call recording, and compliance workflows use Privocio for secure voice transcription. Self-hosted options and retention controls support regulated data environments. Flat-rate pricing provides cost predictability for high-volume usage.

### Legal
Law firms use Privocio for deposition transcription, client intake, and matter workflows. Attorney-client privilege is protected because audio never leaves the firm's infrastructure in self-hosted deployments. DPA support for GDPR compliance.

### Developers
OpenAI SDK compatibility means minimal migration work from OpenAI Whisper. Change `base_url` and keep all existing code. Supports Python, JavaScript, Go, and any language with an HTTP client. Fixed every-4-weeks pricing removes cost uncertainty.

### Meeting Transcription
Real-time streaming with speaker diarization produces meeting notes, action item lists, and searchable meeting archives. Both SSE streaming and batch processing are supported.

### Content Creation
Clean mode produces publication-ready transcripts from interviews, podcasts, and video narration. Filler words, false starts, and noise are removed automatically.

### Customer Support
Support call transcription for quality assurance, training, and compliance. Automatic speaker separation distinguishes between customer and agent speech.

---

## Comparison with Alternatives

| | Privocio | OpenAI Whisper API | Google STT | AWS Transcribe | Deepgram |
|---|---|---|---|---|---|
| Pricing model | Flat-rate / 4 weeks | Per-minute ($0.006/min) | Per-minute | Per-second | Per-minute |
| Data used for training | Never | Possible | Possible | Possible | Possible |
| Self-hosted option | Yes | No | No | No | No |
| Token optimization | Built-in (~60%) | None | None | None | None |
| OpenAI SDK compatible | Yes (drop-in) | Native | No | No | No |
| Streaming | SSE | No | Yes | Yes | Yes |
| Speaker diarization | Yes | No | Yes | Yes | Yes |
| Fixed predictable cost | Yes | No | No | No | No |

**Cost example**: At 200 hours/month, OpenAI Whisper API costs approximately $72/month ($0.006/min × 12,000 min). Privocio Pro covers 800 hours for $39/4 weeks (~$42/month), with no per-minute charges.

---

## Migration from OpenAI Whisper

Migrating from OpenAI Whisper API to Privocio requires changing one line of code:

**Python:**
```python
# Before
client = OpenAI(api_key="openai-key")
# After
client = OpenAI(api_key="privocio-key", base_url="https://api.privocio.com/v1")
```

**JavaScript:**
```javascript
// Before
const client = new OpenAI({ apiKey: "openai-key" });
// After
const client = new OpenAI({ apiKey: "privocio-key", baseURL: "https://api.privocio.com/v1" });
```

All existing API calls, response parsing, and SDK usage remain unchanged.

---

## Security

- **HTTPS-only**: All traffic is encrypted with TLS 1.2+. HTTP is redirected to HTTPS with HSTS preload (max-age=63072000; includeSubDomains; preload).
- **API key authentication**: Keys are scoped per organization and can be rotated from the dashboard.
- **X-Frame-Options: DENY**: Prevents clickjacking.
- **X-Content-Type-Options: nosniff**: Prevents MIME-type sniffing.
- **Security headers**: HSTS, COEP, CSP (in hardening), Referrer-Policy, Permissions-Policy.

---

## System Status

Live API status, uptime history, and incident reports: https://privocio.com/status

---

## API Documentation

Full interactive documentation: https://privocio.com/docs

Includes:
- Authentication (API key and session tokens)
- Transcription endpoint (`POST /v1/audio/transcriptions`)
- Streaming endpoint (SSE)
- TTS endpoint
- Output modes (Raw, Clean, Agent)
- Speaker diarization parameters
- Webhook configuration
- Rate limits per plan
- Error codes and retry guidance

---

## SDKs and Integrations

- **Python SDK**: Use the official `openai` Python package with `base_url="https://api.privocio.com/v1"`. Full guide: https://privocio.com/sdk/python
- **JavaScript SDK**: Use the official `openai` npm package with `baseURL: "https://api.privocio.com/v1"`. Full guide: https://privocio.com/sdk/javascript
- **LangChain integration**: Voice input for LangChain agent chains via OpenAI-compatible client or HTTP. Guide: https://privocio.com/integrations/langchain
- **OpenAI SDK integration**: Full pattern guide: https://privocio.com/integrations/openai-sdk

---

## Supported Languages

100+ languages supported with automatic language detection. Full list: https://privocio.com/en/languages

Includes all major European, Asian, Middle Eastern, and African languages. Medical, legal, and finance vocabulary is handled across supported languages.

---

## Free Transcription Tool

Browser-based transcription tool with no account required: https://privocio.com/free-speech-to-text-stt-online-tool

- Upload MP3, WAV, or M4A files up to 10 MB
- No signup or credit card required
- Up to 3 minutes of audio per transcription on the free tier
- 3 hours of free transcription every 4 weeks

---

## Legal

- **Privacy Policy**: https://privocio.com/legal/privacy-policy
- **Terms of Service**: https://privocio.com/legal/terms-of-service
- **Cookie Policy**: https://privocio.com/legal/cookie-policy
- **Acceptable Use Policy**: https://privocio.com/legal/acceptable-use-policy
- **Data Processing Addendum**: https://privocio.com/legal/data-processing-addendum

---

## Links

- [Homepage](https://privocio.com): Private, flat-rate speech-to-text API overview.
- [Pricing](https://privocio.com/pricing): Flat-rate plans — Free, Go, Pro, Enterprise.
- [API Documentation](https://privocio.com/docs): Authentication, endpoints, streaming, rate limits.
- [Free Transcription Tool](https://privocio.com/free-speech-to-text-stt-online-tool): In-browser audio-to-text, no signup.
- [Supported Languages](https://privocio.com/en/languages): 100+ languages with automatic detection.
- [Blog](https://privocio.com/blog): Guides and technical notes on STT and AI agents.
- [System Status](https://privocio.com/status): Live API uptime and component health.
- [Security Overview](https://privocio.com/security): Encryption, retention, and no model training.
- [Use Cases Hub](https://privocio.com/use-cases): All speech-to-text use cases.
- [Use Case — AI Agents](https://privocio.com/use-cases/ai-agents): Structured voice input for agent frameworks.
- [Use Case — Healthcare](https://privocio.com/use-cases/healthcare): Private clinical transcription.
- [Use Case — Developers](https://privocio.com/use-cases/developers): OpenAI-compatible STT for developers.
- [Use Case — Finance](https://privocio.com/use-cases/finance): Secure voice processing for finance teams.
- [Use Case — Legal](https://privocio.com/use-cases/legal): Privileged audio transcription for legal teams.
- [SDK Hub](https://privocio.com/sdk): Python and JavaScript SDKs.
- [SDK — Python](https://privocio.com/sdk/python): Python transcription guide.
- [SDK — JavaScript](https://privocio.com/sdk/javascript): JavaScript transcription guide.
- [Comparison Hub](https://privocio.com/compare): Compare Privocio to other STT APIs.
- [Privocio vs OpenAI Whisper](https://privocio.com/compare/privocio-vs-openai-whisper): Pricing, privacy, SDK compatibility.
- [Privocio vs AWS Transcribe](https://privocio.com/compare/privocio-vs-aws-transcribe): Flat-rate vs per-second billing.
- [Privocio vs Google STT](https://privocio.com/compare/privocio-vs-google-speech-to-text): TCO and privacy comparison.
- [Migrate from OpenAI Whisper](https://privocio.com/guides/migrate-from-openai-whisper): One-line migration guide.
- [Integrations Hub](https://privocio.com/integrations): Integration patterns for voice workflows.
- [Integration — OpenAI SDK](https://privocio.com/integrations/openai-sdk): Drop-in OpenAI Whisper replacement.
- [Integration — LangChain](https://privocio.com/integrations/langchain): Wire Privocio STT into LangChain.
- [Privacy Policy](https://privocio.com/legal/privacy-policy): How Privocio handles personal data.
- [Terms of Service](https://privocio.com/legal/terms-of-service): Terms for using Privocio services.
- [Data Processing Addendum](https://privocio.com/legal/data-processing-addendum): DPA for enterprise customers.
- [Contact](mailto:hello@privocio.com): Email the Privocio team.