Sprag
sprag.ai
- Web
- API
- Self-hosted
What Sprag is
Sprag provides speech-to-speech agents and a speech recognition, language-model, and speech synthesis pipeline through one API. Its Rhythm service transcribes audio in 30 languages for streaming or batch use. Chorus generates speech with built-in, cloned, or designed voices; Symphony supports realtime agents with tool calling, interruptions, and turn-taking. Symphony Notes describes audio clips, including speech, speakers, emotion, and background sound. Sprag serves its speech models through an OpenAI-shaped HTTP API, so existing clients can connect by changing the base URL and API key. It documents a Pipecat integration and lists LiveKit in its integrations navigation. The service is offered on the web, through an API, and with a self-hosted deployment option. It lists 10 languages and supports MP3, Opus, AAC, FLAC, WAV, and PCM exports. There is no free plan. Chorus stock-voice generation is listed at $0.70 per hour of speech generated; voice design and cloning have separate listed charges. Sprag says data is stored in its cloud infrastructure, transfers use HTTPS/TLS, and Stripe processes payment card details rather than Sprag storing them.
Who it suits
Sprag is intended for developers aged 16 and older who need speech recognition, synthesis, or realtime voice agents. It offers web, API, and self-hosted access options.
Good to know, and what to watch
- Rhythm supports streaming and batch transcription.
- Chorus offers built-in, cloned, or designed voices.
- Symphony supports realtime tool calling and turn-taking.
- Six listed audio export formats.
- Self-hosted deployment option is linked.
- No free plan is listed.
- Realtime Rhythm and Symphony sessions cost 25% above batch rates.
- Payment card details are processed by Stripe.
Plans
Every plan and priceChorus
Chorus Design
Chorus Clone
Symphony Notes
Getting started
- Open the Sprag website
- Choose web, API, or self-hosted deployment
- Select a paid service such as Chorus, Rhythm, or Symphony
- For API clients, change the base URL and API key
- Connect documented integrations such as Pipecat where needed
Limits to check
Sprag has no free plan. Realtime Rhythm and Symphony sessions are billed at 25% above their batch rates, while speech output costs the same either way.
The verdict
Sprag combines transcription, speech generation, audio descriptions, and realtime agents behind an API. Review the separate usage charges and realtime rate premium when choosing which services to use.
Questions people ask
Does Sprag have a free plan?
No. Sprag lists paid plans only.
What platforms can I use?
Sprag is available on the web, through an API, and with a self-hosted deployment option.
Does Sprag support voice cloning?
Yes. Chorus Clone clones a voice from a short reference, and the listed plan adds $1.00 per hour of input audio.
Which languages does Sprag support for speech recognition?
Rhythm transcribes audio in 30 languages.
What does Chorus cost?
The Chorus plan is listed at $0.70 a month, billed at $0.70 per hour of speech generated, and also at $19.44 per 1M audio tokens.
Is Sprag's API compatible with OpenAI clients?
Sprag provides an OpenAI-shaped HTTP API. Existing clients can connect by changing the base URL and API key.
What the maker publishes
- API access
- Yes source
- API compatibility
- Sprag serves speech models through an OpenAI-shaped HTTP API, and existing clients can point to it by changing the base URL and API key. source
- Audience
- Sprag says its products and services are intended for developers aged 16 and older. source
- Captioning
- Symphony Notes describes audio clips, including speech, speakers, emotion, and background sound. source
- Enterprise
- The pricing page says users can contact Sprag for an organization account for enterprise use. source
- Export formats
- mp3,opus,aac,flac,wav,pcm source
- Free plan
- No source
- Integrations
- Sprag documents integration with Pipecat using its OpenAI services and lists LiveKit in its integrations navigation. source
- Languages
- 10 source
- Limit
- The pricing page says realtime sessions bill at 25% above batch rates for Rhythm and Symphony, while speech output costs the same either way. source
- Platforms
- web,api source
- Privacy and security
- Sprag says data is stored in its cloud infrastructure, transfers use HTTPS/TLS, and payment card details are processed by Stripe rather than stored on its systems. source
- Privacy controls
- Sprag says it does not sell personal information and provides California residents an opt-out for advertising-measurement cookies that may constitute sharing. source
- Product
- Sprag offers native speech-to-speech agents and an STT-to-LLM-to-TTS voice pipeline through one API. source
- Realtime agents
- Symphony supports realtime tool calling and natural interruptions and turn-taking. source
- Self-hosting
- The homepage links to a self-hosted deployment option. source
- Speech recognition
- Rhythm transcribes audio in 30 languages and supports streaming and batch use. source
- Speech synthesis
- Chorus synthesizes speech using a built-in, cloned, or designed voice. source
- Support
- The pricing page directs users with questions about account costs, billing, rate limits, enterprise agreements, and metering to contact Sprag. source
- Voice cloning
- Yes source
Checked against the maker's pages on 7 Oct 2026.