Azure AI Speech text-to-speech vs Murf TTS API + MCP

Azure AI Speech text-to-speech

Real-time synthesis keeps neither the input text nor the output audio. An Azure subscription needs a card, even for the free F0 tier.

Murf TTS API + MCP

Falcon 2 costs 1 cent per 1,000 characters on pay as you go, with a $2 minimum purchase. Falcon 2 concurrency is 2 outside US-East on free and pay as you go, 5 on US-East.

Azure AI Speech text-to-speech

1. Send SSML with <speak> and <voice>, and set X-Microsoft-OutputFormat and User-Agent.
2. On 429 retry with backoff, and try the voice's home region or another region rather than asking for more quota.
3. Keep each real-time request under 10 minutes of audio, or use batch synthesis.
4. Use Entra ID tokens instead of resource keys where the agent runs inside Azure.
5. Cache the voice list per region, since it returns hundreds of entries at once.

Murf TTS API + MCP

1. Send locale on every request, since multiNativeLocale was replaced on 2026-03-05.
2. Split text into chunks under 3,000 characters per request.
3. Use the US-East host for 5 concurrent Falcon 2 calls instead of 2.
4. Set encodedAsBase64 to get audio inline and skip the expiring download link.
5. Back off on 429 and close WebSocket contexts with end: true to free slots.