Compare realtime APIs
Pick up to four APIs from any category and see them side by side.
| Google Cloud Text-to-Speech (Chirp 3 HD and Gemini-TTS) Google Cloud | Murf Falcon / Falcon 2 Murf AI | ElevenLabs TTS API ElevenLabs | |
|---|---|---|---|
| Category | Text-to-speech | Text-to-speech | Text-to-speech |
| Status | GA | GA | GA |
| Est. per minute | $0.009 - 0.03 | $0.009 - 0.01 | $0.0099 - 0.072 |
| How that was worked out | Chirp 3 HD: 900 chars x $30/1M = $0.027. Gemini: 60 s x 25 tokens = 1,500 audio tokens/min; 3.8 Flash-Lite $0.009, 3.8 Flash $0.0135 (promo), 2.5 Flash $0.015, 2.5 Pro $0.03 (text input cost negligible). | Vendor headline 1 cent/min; 900 chars x $0.01/1K = $0.009 | 900 chars/min. Low = v4 Turbo promo rate ($0.011/1K, ends Oct 12 2026; $0.036/min after). Flash v2.5 = $0.036/min. High = v3 or Multilingual v2 at $0.08/1K. |
| Pricing model | per-character | per-character | per-character |
| Free tier | Chirp 3 HD: 1M characters/month; WaveNet/Standard 4M; Gemini-TTS: none | Third-party sources conflict ($10 monthly credit vs 100K-character trial) | Free / pay-as-you-go: 10,000-20,000 characters depending on model. Commercial-use terms on the free tier not re-verified; check the plan terms. |
| Connects by | gRPC, HTTP chunked | WebSocket, HTTP chunked | WebSocket, HTTP chunked |
| Audio in | Text, SSML (legacy voices), natural-language prompt for Gemini-TTS | Text | Text (SSML parsing optional via enable_ssml_parsing on the WebSocket) |
| Audio out | Streaming: PCM (default), ALAW, MULAW, OGG_OPUS. Batch: LINEAR16, ALAW, MULAW, MP3, OGG_OPUS, PCM. | WAV or PCM (16-bit LE), example sample_rate 24000, MONO | MP3 by default; output_format values follow codec_samplerate_bitrate, e.g. mp3_44100_128, pcm_16000/22050/24000/44100, ulaw_8000, alaw_8000, opus_48000_* (format list from third-party mirrors of the API reference; some higher-quality formats are tier-gated) |
| Languages | Chirp 3 HD: 53 locales; Gemini-TTS: see per-model list | 35+ (vendor) | Flash v2.5: 32; v3: 70+; v4: 90+ |
| Latency (vendor claim) | No numeric claim on the pages checked; Gemini-TTS described as 'very low latency'. | Vendor: Falcon 55 ms model latency / 130 ms TTFA; Falcon 2 sub-100 ms TTFA. | Vendor claims: Flash v2.5 ~75 ms model latency, v4 Turbo ~100 ms median inference, v3 conversational ~280 ms. All exclude network and application latency. |
| Key limits |
|
|
|
| High-severity warnings |
|
|
|
| Compliance | Google Cloud data terms and regional endpoints; certifications not re-verified here. | Not verified. | Data-residency endpoints for EU, India and Singapore exist. Certifications not re-verified in this pass. |
| Self-hostable | No | No | No |
| Last checked | 2026-10-10 | 2026-10-10 | 2026-10-10 |
| Key numbers and features | |||
| $/1M chars | $30 | $10 | $40 |
| Free tier | Yes | - | Yes |
| Free credit $ | - | - | - |
| Free tier commercial | - | - | - |
| Voices | 30 | - | - |
| Cloning | Yes | - | Yes |
| Instant clone | Yes | - | - |
| Text stream in | Yes | Yes | Yes |
| Timestamps | - | Yes | Yes |
| Emotion | Yes | Yes | - |
| SSML | Yes | - | Yes |
| 8 kHz phone | Yes | - | Yes |
| Latency ms | - | 100 | 75 |
| Languages | - | 35 | 32 |
| Max session min | - | - | - |
| Concurrency | - | 5 | 6 |
| WebRTC | No | No | No |
| WebSocket | No | Yes | Yes |
| gRPC | Yes | No | No |
| HIPAA | - | - | - |
| SOC 2 | - | - | - |
| EU data | Yes | Yes | Yes |
| Self-host | No | No | No |
| Open weights | No | No | No |
| High warnings | 2 | 1 | 2 |