Piper (Rhasspy)
Fast, on-device neural TTS optimized for Raspberry Pi 4.
Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min
Upstream is archived. Piper (Rhasspy)’s repository has been set read-only by its owner, so there are no further releases, fixes, or security patches. The last commit landed 2025-08-26. It can still be cloned and run, and forks may be maintained elsewhere. See the repository.
Best for home Assistant / Wyoming-protocol setups needing fast offline TTS on a Pi 4. Pricing: free (MIT).
What it is
Piper is Rhasspy's current-generation TTS, optimized for Raspberry Pi 4-class hardware. Wyoming-protocol support makes it a drop-in TTS for Home Assistant Assist alongside Vosk for STT. 30+ languages and ~100 voices. MIT. Consent posture: synthetic-only — no cloning surface.
Watch out for: Synthetic voices only — no cloning surface.
Install / use
Download from github.com/rhasspy/piper/releases
Features
| Speaker diarization | No |
| Word-level timestamps | No |
| Streaming / real-time | No |
| Languages supported | 30 |
| HIPAA eligible | No |
Links
Piper (Rhasspy) vs Whipscribe
| Feature | Piper (Rhasspy) | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free (MIT) | $4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup |
| Speaker diarization | — | Yes |
| Word timestamps | — | Yes |
| Streaming | — | No |
| Languages | 30 | 99 |
| Platforms | Linux, macOS, Windows, Raspberry Pi | Web, API, MCP |
Alternatives to Piper (Rhasspy)
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.