- Home
- Text-to-speech tools
- Sprag
Sprag
What it is
Sprag offers speech-to-speech agents and a speech recognition, language-model, and speech synthesis pipeline through one API. Rhythm transcribes audio in 30 languages for streaming or batch use. Chorus creates speech with built-in, cloned, or designed voices, while Symphony supports realtime tool calling, interruptions, and turn-taking. Symphony Notes describes audio clips, including speech, speakers, emotion, and background sound. Sprag provides speech models through an OpenAI-shaped HTTP API; existing clients can connect by changing the base URL and API key. It documents integration with Pipecat and lists LiveKit in its integrations navigation. The service is available through API, web, and a self-hosted deployment option. Voice cloning and API access are supported, and audio exports include MP3, Opus, AAC, FLAC, WAV, and PCM. There is no free plan. Chorus is listed at $0.70 per month, billed at $0.70 per hour of generated speech; other listed options cover voice design, cloning, transcription, realtime agents, and captioning. Sprag says realtime sessions for Rhythm and Symphony cost 25% above batch rates.
For and against
For
- Rhythm supports streaming and batch transcription in 30 languages.
- Chorus supports built-in, cloned, and designed voices.
- Symphony supports realtime tool calling and turn-taking.
- Exports include MP3, Opus, AAC, FLAC, WAV, and PCM.
Against
- There is no free plan.
- Realtime Rhythm and Symphony sessions cost 25% above batch rates.
- Chorus is billed at $0.70 per hour of generated speech.
The verdict
Sprag covers transcription, voice generation, captioning, and realtime agents through its API. There is no free plan, and realtime sessions have higher rates than batch use.
Who it suits
Sprag is intended for developers aged 16 and older who need speech recognition, synthesis, or realtime voice agents through an API. Its web and self-hosted options offer additional ways to deploy or access the service.
Plans and prices
Chorus
Stock-voice text-to-speech
Read 20 Sep 2026 · sprag.ai
Chorus Design
Designs new voices from a text prompt
Read 20 Sep 2026 · sprag.ai
Chorus Clone
Clones a voice from a short reference
Read 20 Sep 2026 · sprag.ai
Symphony Notes
Audio captioning · + $2.03 per 1M output tokens
Read 7 Oct 2026 · sprag.ai
Rhythm
Streaming and batch · realtime sessions cost 25% over batch rates
Read 7 Oct 2026 · sprag.ai
Symphony
Text, image, audio, and video in · text and speech out · tool calling · realtime sessions cost 25% over batch rates
Read 7 Oct 2026 · sprag.ai
Chorus — built-in voice
Built-in voices · $19.44 per 1M audio tokens
Read 7 Oct 2026 · sprag.ai
Chorus — cloned voice
$0.27 per hour of speech · + $1.00 per hour of reference audio
Read 7 Oct 2026 · sprag.ai
Chorus — designed voice
Voice design
Read 7 Oct 2026 · sprag.ai
On the record
- API access
- Yessprag.ai · read 20 Sep 2026
- 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.sprag.ai · read 7 Oct 2026
- Audience
- Sprag says its products and services are intended for developers aged 16 and older.sprag.ai · read 7 Oct 2026
- Captioning
- Symphony Notes describes audio clips, including speech, speakers, emotion, and background sound.sprag.ai · read 7 Oct 2026
- Enterprise
- The pricing page says users can contact Sprag for an organization account for enterprise use.sprag.ai · read 7 Oct 2026
- Export formats
- mp3,opus,aac,flac,wav,pcmsprag.ai · read 20 Sep 2026
- Integrations
- Sprag documents integration with Pipecat using its OpenAI services and lists LiveKit in its integrations navigation.sprag.ai · read 7 Oct 2026
- Languages
- 10sprag.ai · read 20 Sep 2026
- 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.sprag.ai · read 7 Oct 2026
- 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.sprag.ai · read 7 Oct 2026
- 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.sprag.ai · read 7 Oct 2026
- Product
- Sprag offers native speech-to-speech agents and an STT-to-LLM-to-TTS voice pipeline through one API.sprag.ai · read 7 Oct 2026
- Realtime agents
- Symphony supports realtime tool calling and natural interruptions and turn-taking.sprag.ai · read 7 Oct 2026
- Self-hosting
- The homepage links to a self-hosted deployment option.sprag.ai · read 7 Oct 2026
- Speech recognition
- Rhythm transcribes audio in 30 languages and supports streaming and batch use.sprag.ai · read 7 Oct 2026
- Speech synthesis
- Chorus synthesizes speech using a built-in, cloned, or designed voice.sprag.ai · read 7 Oct 2026
- Support
- The pricing page directs users with questions about account costs, billing, rate limits, enterprise agreements, and metering to contact Sprag.sprag.ai · read 7 Oct 2026
- Voice cloning
- Yessprag.ai · read 20 Sep 2026
