AssemblyAI
Transcription API with built-in audio intelligence features
Verdict
Excellent transcription with audio intelligence layered on top — sentiment analysis, topic detection, PII redaction, summarization. Universal-2 model handles accents and noise well.
Other Speech & Audio
- BarkStable
Open-source TTS model with emotions, music, and sound effects
- Coqui TTSExperimental
Open-source TTS toolkit for training and deploying custom voices
- DeepgramProduction
Real-time speech-to-text API with sub-300ms latency
- ElevenLabsProduction
Best-in-class text-to-speech with voice cloning and dubbing
- Kokoro TTSExperimental
Lightweight 82M-parameter open-source text-to-speech model
- OpenAI TTSProduction
OpenAI's simple API for high-quality speech synthesis